Activation Steering

Follow this topic Ask about this topic

Activation steering studies how edits to a model’s hidden activations can control its behavior at inference time, enabling changes without retraining the full model. Common approaches add or remove contrastive steering vectors, target sparse autoencoder features, neurons or attention heads, and use conditional or feedback-based controllers to adapt interventions to the input or generation state. Researchers apply these methods to language tasks such as reasoning, refusal, factuality and hallucination mitigation, as well as image and video generation, speech, and embodied agents; evaluations include benchmarks such as GSM8K, TruthfulQA, POPE and LIBERO. A central challenge is that readable or decodable features are not necessarily controllable, and effective edits can vary by context and architecture or cause collateral changes to fluency, utility and safety.

Latest papers

376 papers77 papers in the last four weeks, up 93% on the four weeks before. 0.5% of all new papers.

Jun 27, 2026

Mechanistic Personality Analysis of LLMs Steering Personality via Latent Feature Interventions

Large Language Models (LLMs) have demonstrated the ability to simulate human-like OCEAN personality traits in generated text. Previous efforts have focused on prompt engineering or fine-tuning to shape LLM personality. In this work, we propose a mechanistic interpretability approach that directly intervenes on the model's latent features. Our method identifies latent directions in the residual stream corresponding to a target OCEAN trait using sparse autoencoders (SAEs) and contrastive activation analysis. We formalize an additive steering vector in activation space and demonstrate how applying a small additive shift to the hidden states enhances the target trait while preserving overall language modeling performance. To determine the optimal combination of feature shifts, we explore a linear weighting heuristic with grid search optimization that balances personality expression with task performance. Our approach shows promise in controllably steering personality traits at the mechanistic level while maintaining high performance on standard benchmarks.

David Courtis, Ting Hu

Department of Computing, Queen’s University Kingston, Kingston, ON, Canada.

Language Model Steering LLM Interpretability Personality Modeling in Language Models Causal Interventions in Language Models Activation Steering

Jun 26, 2026

SPARK: Adaptive Parametric Knowledge Participation for Faithful Retrieval-Augmented Generation

Retrieval-augmented generation (RAG) enhances the faithfulness of large language models (LLMs) by incorporating external knowledge into the generation process. However, conflicts between retrieved context and parametric knowledge can cause LLMs to rely on inconsistent internal knowledge, hindering their ability to faithfully leverage retrieved evidence. Existing approaches mitigate this issue by editing parametric knowledge to resolve such conflicts. However, locating and modifying knowledge encoded in model parameters is challenging and may inadvertently compromise the backbone LLM's capabilities. In this paper, we introduce SPARK, a novel framework that formulates parametric knowledge control as a latent participation policy learning problem, enabling LLMs to adaptively regulate the contribution of parametric knowledge during generation. Specifically, SPARK introduces a lightweight participation policy that dynamically modulates the contribution of FFN-mediated parametric knowledge while keeping the backbone LLM frozen. The participation policy is optimized with a faithfulness-oriented reward, enabling fine-grained control over parametric knowledge participation during generation. Extensive experiments on six datasets validate the effectiveness of SPARK, which introduces and optimizes only 0.01% additional trainable parameters while keeping the backbone LLM fully frozen, thereby preserving its general capabilities and achieving more faithful generation than competitive baselines. All datasets and code are available at https://github.com/OpenBMB/SHIFT.

Ruochang Li, Pengcheng Huang, Zhenghao Liu +5

School of Computer Science and Engineering, Northeastern University, Shenyang, China · Department of Computer Science and Technology, Tsinghua University, Beijing, China

Retrieval-Augmented Generation Knowledge Conflicts in Language Models Activation Steering

Jun 25, 2026

Localizing RL-Induced Tool Use to a Single Crosscoder Feature

Fine-tuning through RL reshapes the internal representations of language models to enable agentic behaviors such as tool use, yet the mechanistic basis of these changes remains poorly understood. While RL substantially improves structured tool-call generation, it is unclear which features emerge, which are preserved, and whether identified features can be leveraged for retraining-free behavioral control. In this work, we show that

\textit{Dedicated Feature Crosscoders (DFC)}

isolate a compact set of RL-specific features that mediate tool-calling capability in

\texttt{Qwen2.5-3B}

. Across a

48

-crosscoder hyperparameter sweep, encode-decode reconstruction improves the RL model's tool correctness by

+31.1 \pm {9.7}

pp and passively transfers tool-calling ability to the frozen base model by

+6.8 \pm 5.0

pp which we call a

\textit{capability spillover}

. Our findings show that DFC partitioning concentrates RL-introduced capability into a minimal, steerable feature set that enables runtime behavioral control of agentic LLMs.

Andrii Shportko, Shubham Bhokare, Ahmed Zeyad A Alzahrani +3

1Northwestern University.

LLM Interpretability LLM Tool Use Activation Steering RL for Tool Use

Jun 24, 2026

Refusal Lives Downstream of Persona in Chat Models

Linear directions in activation space have been identified for both refusal and persona traits in instruction-tuned chat models, but the two have been studied as separate mechanisms. We show they interact: a compliant persona gates refusal. In Qwen2.5-7B-Instruct and Llama-3.1-8B-Instruct, we extract a compliant model-persona direction and a refusal direction and intervene on both. Compliant persona steering suppresses refusal -- in Llama, the refusal rate falls from 97% to 2%. Reintroducing the refusal direction partially restores refusal at late layers but not at early ones. Projecting out the persona direction in a late-layer window restores it to baseline; projecting out a random direction does not. Refusal is therefore gated at the late-layer expression stage, downstream of where it is computed. Treating refusal as a single isolated direction misses its dependence on persona.

Viola Zhong, Qirui Li

Independent · Department of Mathematics Pohang University of Science and Technology

Language Model Steering LLM Refusal Behavior Causal Interventions in Language Models Persona-Conditioned Generation Refusal Behavior in Language Models Activation Steering+1

Jun 23, 2026

Detecting and Controlling Sycophancy with Cascading Linear Features

Interpreting and controlling model behaviors through activation steering methods requires many pairs of contrastive samples that clearly exhibit desired or undesired behavior. These data pairs determine the degree to which interpretability frameworks can reliably detect model features responsible for a behavior, and therefore the ability to steer models toward or away from such behavior. In this work, we present an iterative data generation pipeline that isolates cascading linear features responsible for a behavior. Specifically, we show how moving beyond simple binary pairs of samples, and instead isolating samples that show degrees of features that scale linearly with behavior, allows for better disentanglement of features. We focus on detecting and steering away from sycophancy -- the tendency of language models to prioritize user validation. We demonstrate that sycophancy features discovered through cascading samples form linearly separable subspaces, and allow for selection of model activations that more clearly correspond to the desired behavior than baseline approaches. We also evaluate their ability to enable detection, deterministic scoring, and robust steering, and see that they either match or outperform LLM-as-a-judge and system prompting baselines while providing lower computational demand and more interpretability guarantees. Code & Data: https://cascading-feats.github.io/

Maty Bohacek, Rishub Jain, Nicholas Dufour +3

Stanford University · Google DeepMind

LLM Sycophancy Language Model Steering LLM Interpretability Activation Steering

Jun 23, 2026

Parallel Manifold Steering: Efficient Adaptation of Large Associative Memories via Residual Energy Shaping

Large Transformer models function as Dense Associative Memories (DAMs), retrieving knowledge via high-dimensional attractor dynamics driven by the self-attention mechanism \citep{ramsauer2020hopfield, wu2024attention}. However, adapting these frozen memory systems to new tasks presents a fundamental ``Plasticity-Stability'' dilemma. Current methods either risk catastrophic interference by modifying synaptic weights directly (e.g., LoRA) \citep{hu2021lora} or degrade associative capacity by clogging the retrieval buffer with static prompt tokens (e.g., VPT) \citep{jia2022vpt}. In this work, we propose H-Res (Hierarchical Residual Steering), a mechanism that modulates the effective energy landscape of the Transformer without altering its global equilibrium or expanding its sequence length. By formulating adaptation as a control problem on the activation manifold \citep{chen2018neuralode}, H-Res learns a state-dependent vector field that steers token trajectories into task-specific basins of attraction. We formally prove that H-Res preserves the attention entropy of the foundation model and facilitates Neural Collapse \citep{papyan2020prevalence}. Empirically, Manifold Steering outperforms global weight modification by 26% on associative retrieval tasks and eliminates the computational overhead of prompt-based methods, scaling effectively to structured domains \citep{zha2023vtab}.

Kanishk Awadhiya

Independent Researcher

Memory-Augmented Neural Networks Transformer Attention Activation Steering Associative Memory Parameter-Efficient Fine-Tuning

Jun 23, 2026

Perfect Detection, Failed Control: The Geometry of Knowing vs. Steering in Language Models

A central aspiration of mechanistic interpretability is controllability: if we know where a behavior is represented in a model's activations, we should be able to modify it. This rests on a hidden premise -- that the direction which detects a behavior and the direction which controls it are the same, or close. We test this geometrically: what is the angle between the direction that best detects a behavior and the one that best causes it? If detection implies control the cosine is near 1; otherwise it quantifies a detection-intervention gap. On Gemma 2-2B-it, output format (clean JSON vs markdown fencing) collapses both roles onto one axis. Hallucination does not: the model detects fake entities with perfect linear separability (AUC = 1.000 from layer 5), yet that direction sits at cos = 0.12 (about 83 degrees) from the direction producing a refusal -- a small, reproducible alignment, far from the cos = 1 that "detection is control" would require. A detector built from activations, with no chosen tokens, likewise fails to align (cos = -0.06). The gap generalizes: across four models from three families and two scales (1B-9B), cos stays in [0.12, 0.20], identical before and after instruction tuning (0.1197 vs 0.1200), placing its origin in pretraining. A 15-degree rotation toward the refusal direction partially bridges it -- 73% and 60% refusal on two held-out fake-entity categories at 1.8% false positives. We then ask whether this cosine predicts steerability, and it does not: detection is a high-dimensional class, not a single direction, and what separates the steerable case is functional, not readable from a static angle. The cosine is a weight-computable signature of the dissociation between knowing and steering, not a predictor of it.

Cosimo Galeone, Anna Ettorre, Minsu Park +2

Alomana, Grottaglie, Italy

Mechanistic Interpretability Causal Interventions in Language Models Representation Geometry in Language Models Activation Steering

Jun 21, 2026

Agent MechSuits: Mechanistic Subspace Safety Steering for Multi-Turn CLI Agents

Command-Line Interface (CLI) agents based on large language models (LLMs) demonstrate remarkable autonomous capabilities, but they also introduce significant safety and misuse risks during multi-turn interactions with external environments. Existing safety mechanisms mainly rely on external guardrails, which have a limited ability to perform fine-grained behavioral control during execution. Meanwhile, recent mechanistic interpretability methods for LLM safety are mostly confined to single-turn or jailbreak-style QA settings, limiting their ability to capture the evolving risk dynamics of multi-turn agent execution. In this paper, we investigate the safety of multi-turn CLI agents from an internal perspective. We propose Agent MechSuits (Mechanistic Subspace Intervention and Steering), a white-box defense framework that performs runtime safety detection and representation-level mitigation for CLI agents. Unlike conventional agent guardrails, Agent MechSuits detects harmful execution states from step-level hidden representations and mitigates unsafe behavior by intervening in a 10-dimensional subspace within a single layer. To support this research, we introduce the Mechanistic Agent Safety (MAS) benchmark, comprising comprehensively annotated multi-turn execution trajectories across 194 tasks using LLaMA-3.1-8B, Qwen-2.5-7B, and Gemma-2-9B. Extensive experiments show that Agent MechSuits achieves strong safety detection performance, provides preliminary evidence for lookahead risk anticipation, and substantially reduces harmful actions of the CLI agent, establishing a foundation for applying mechanistic interpretability to dynamic LLM agent safety.

Weidi Luo, Qiming Zhang, Yihao Quan +5

University of Georgia · University of South Florida · Rutgers University +3

Computer-Use Agents LLM Interpretability AI Agent Safety Benchmarks LLM Agent Safety Activation Steering

Jun 21, 2026

ORBIT: Training-Free Multi-Attribute Behavioral Steering via Orthogonal Subspace Rotation

Language models are widely used in assistant settings, where controlling behavioral attributes is often essential. Activation steering modifies hidden-state representations at inference time, providing a lightweight, training-free mechanism that can be toggled at runtime. Existing methods, however, have focused primarily on steering a single attribute at a time. When multiple attributes must be controlled simultaneously, naive summation of per-attribute steering vectors suffers from norm imbalance and directional cancellation, while classifier-based approaches require retraining whenever the attribute set changes. We introduce ORBIT (Orthogonal Rotation-Based Intervention Technique), a training-free extension of rotation-based steering to the multi-attribute setting. Our method constructs a joint subspace from per-attribute steering planes via singular value decomposition and applies a single norm-preserving rotation within that subspace toward a combined target direction. Adaptive per-token gating identifies which attributes need correction at each position, and an optional additive boost strengthens attributes with weak initial projection. We also introduce TraitFactory, a new multi-attribute benchmark that focuses on behavioral tendencies rather than surface-level style. We evaluate ORBIT on TraitFactory and ToneBank across three models (Llama-3.2-3B, Qwen-2.5-7B, Llama-3.1-8B) while steering multiple attributes simultaneously, showing that it achieves stronger and more balanced multi-attribute steering than existing training-free baselines while better preserving output coherence.

Narges Ghasemi, Amir Ziashahabi, Salman Avestimehr +1

1Information Sciences Institute, University of Southern California · Department of Electrical and Computer Engineering, University of Southern California

Language Model Steering Activation Steering

Jun 18, 2026

Right Knowledge, Wrong Answer: Test-Time Steering for Temporal Fact Conflicts in Open-Weight Language Models

Large language models can store both outdated facts and newer superseding facts in their parameters, but standard prompting may still elicit the outdated answer. We formalize this problem as Parametric Temporal Conflict (PTC) and introduce Temporal Attractor Steering (TAS), a three-stage test-time intervention that detects likely conflicts, identifies a conflict-critical layer, and steers hidden states toward newer-fact representations without retraining or external retrieval. We construct an 8,746-record verified benchmark across five Wikidata relations and evaluate four open-weight language models from three families: Qwen-2.5-1.5B/7B, Mistral-7B-v0.3, and Llama-3.1-8B. Single-layer activation patching achieves answer-flip rates of 0.72-0.85 across all models. End-to-end TAS resolves 29-57% of PTC cases while preserving 85-99% accuracy on non-conflict queries, outperforming a matched ITI baseline on three of four models. These results show that outdated parametric knowledge can be selectively overridden at inference time.

Elias Hossain, Sourav Saha, Umesh Chandra Biswas +1

University of Central Florida · 2Mississippi State University

Knowledge Conflicts in Language Models Temporal Reasoning in Language Models Factual Knowledge in Language Models Causal Interventions in Language Models Activation Steering Temporal QA

Jun 18, 2026

Translating Inference-Time Control to Radiology Vision-Language Models: Activation Steering for Pneumonia Classification on Chest X-rays

Inference-time engineering can alter model behavior without fine-tuning. However, its utility for improving diagnostic performance in medical vision-language models (VLMs) remains unclear. We aim to evaluate whether Contrastive Activation Addition (CAA) can improve pneumonia classification in chest radiograph VLMs without updating model weights. Three frozen chest radiograph VLMs (MedGemma-4B-IT, NV-Reason-CXR-3B, and CheXOne-3B) were evaluated on the public Kermany pneumonia test set. Classification was based on the logits of the tokens Yes and No under a binary prompt. Steering vectors included a 30-pair answer-bias control, a 30-pair pneumonia text contrast, and an image-conditioned contrast derived from 30 pneumonia and 30 normal development images. A deterministic 200-image development set was used for layer and scale selection (100 images) and threshold calibration (100 images). Performance was assessed using ROC-AUC, PR-AUC, F1 score, threshold analyses, reverse-vector controls, random-vector controls, and conditional bootstrap confidence intervals. Fixed-threshold F1 improvements were frequently observed but did not consistently indicate improved diagnostic performance. For MedGemma-4B-IT. NV-Reason-CXR-3B showed the strongest benefit: calibrated F1 improved from 0.7692 in the zero-shot setting to 0.8619 with pneumonia-text steering and to 0.8727 with image-conditioned steering. For CheXOne-3B, pneumonia-text steering increased calibrated F1 from 0.8528 to 0.8666, although the confidence interval crossed zero. On this public pneumonia benchmark, CAA substantially altered prediction score distributions and operating characteristics without fine-tuning. Meaningful performance gains were observed in one of three evaluated VLMs, suggesting that activation steering may serve as a lightweight approach for adapting medical VLM behavior.

Eduardo Moreno Judice de Mattos Farina, Mateus A. Esmeraldo, Felipe Akio Matsuoka +2

Universidade Federal de São Paulo (UNIFESP) Hospital Israelita Albert Einstein São Paulo, Brazil · Department of Radiology Stanford University School of Medicine Stanford, CA, USA · Universidade Federal de São Paulo (UNIFESP) DASA São Paulo, Brazil +2

Chest X-Ray Classification Radiology VLMs VLM Adaptation Medical Image Classification Activation Steering

Jun 18, 2026

Actionable Activation Directions for Detecting and Mitigating Emergent Misalignment Across Language Model Families

Fine-tuning language models on insecure code induces emergent misalignment with poorly understood internal structure. We investigate whether this misalignment corresponds to a causally actionable activation-space direction shared across architectures. Across four instruction-tuned model families (Qwen2.5-1.5B, Gemma-2-2B, Llama-3.2-1B, Ministral-3-3B) finetuned identically, a difference-in-means direction achieves 99.6% separation of aligned and misaligned activations at each model's final layer. Causal steering by subtracting this direction reduces code spillover by 21-51 points, while a secure-code control confirms content specificity. Cross-architecture transfer via ridge regression maps yields large behavioral suppression (up to 46 points) but fails specificity controls as random and orthogonal directions perform comparably. We identify a two-tier specificity structure: within-model directions are causally specific and actionable; cross-model directions are causally real but non-specific. An asymmetric transfer topology emerges, with Gemma and Qwen acting as geometric donors and Llama as a receiver. These findings define the limits of linear cross-architecture correction and recommend within-model probing for auditing.

Abdul Rafay Syed

Department of Computer Science Universität des Saarlandes Saarbrücken, Germany

LLM Auditing Emergent Misalignment in Language Models LLM Safety Emergent Misalignment Causal Interventions in Language Models Activation Steering

Jun 18, 2026

GEMS: Geometric Constraints Enable Multi-Semantic Superposition in LLMs

Activation steering controls model behavior by modifying intermediate hidden states at inference time without retraining. Existing methods handle only single-direction injection; when multiple semantic directions are superposed without constraints, the model collapses. We show that this collapse decomposes into two independently acting sources: distributional deviation, where additive perturbations accumulate in norm across layers and drive activations outside the training distribution, and directional interference, where non-orthogonal semantic vectors mutually dampen when superposed. These two sources define the design constraints that any training-free multi-directional intervention must address. As one instantiation of these principles, we propose GEMS, a training-free method that maps each source to a corresponding geometric constraint: norm-preserving weighted superposition and targeted attention-pathway injection for distributional deviation, and real-time orthogonalization for directional interference. On GSM8K, injecting three concurrent non-mathematical directions preserves accuracy at 98% (baseline 92%), while unconstrained addition collapses to 4%; on Wikitext-2, the same injection incurs only 2.2% PPL increase. Component ablation isolates the causal role of each constraint, and layer-level probes confirm that orthogonalized signals survive the FFN pathway and reach the output distribution with semantic specificity. Qualitative steering effects transfer across architectures from 3B to 31B.

Yu Deng

Causal Interventions in Language Models Representation Geometry in Language Models Activation Steering

Jun 17, 2026

Closing the Loop: PID Feedback Control for Interpretable Activation Steering in Symbolic Music Generation

Transformer-based architectures have significantly advanced the generation of complex symbolic sequences, yet a significant gap remains in achieving fine-grained, interpretable control over discrete signal attributes. This paper investigates the mechanistic interpretability of the Multitrack Music Transformer (MMT) and proposes a framework for deterministic attribute modulation without retraining to bridge this gap via inference-time activation steering. Utilizing the Difference-in-Means (DiffMean) methodology, we isolate latent directions for signal attributes, specifically Pitch and Duration, within the residual stream. We validate the Linear Representation Hypothesis in this domain, achieving high correlation between steering magnitude and attribute shift. To address the inherent feature entanglement in multi-attribute steering, we introduce a Dual Steering framework utilizing Gram-Schmidt Orthogonalization. Experimental results demonstrate that this geometric decoupling reduces conceptual interference and signal degradation compared to naive vector addition, enabling independent deterministic control even against strong autoregressive conditioning.

Ioannis Prokopiou, Pantelis Vikatos, Maximos Kaliakatsos-Papakostas +2

Athens University of Economics and Business, Athens, Greece · Orfium Research, Athens, Greece · Hellenic Mediterranean University, Chania, Greece +2

Transformer Interpretability Controllable Music Generation Linear Representation Hypothesis Symbolic Music Generation Activation Steering

Jun 16, 2026

Want Better Synthetic Data? Steer It: Activation Steering for Low-Resource Language Generation

Large language models (LLMs) have become an effective tool for synthetic data generation, including for low-resource languages, where generated data can improve downstream task performance. Current best-performing approaches typically rely on few-shot prompting with target-language examples, which increases inference costs and may reduce diversity through lexical anchoring. In this work, we investigate activation steering as an alternative for low-resource synthetic data generation. We study two steering strategies: Language Steering, which targets the linguistic identity of a language, and Quality Steering, which captures well-formedness by contrasting human-written and backtranslated text representations. We evaluate these methods across four open-source LLMs, multiple layers, and 11 typologically diverse languages by generating sentiment and topic classification data and finetuning smaller classifiers. Steering is applied in both zero-shot and few-shot prompting settings and compared against non-steered counterparts. Our results show that steering on early layers consistently improves the diversity of generated data while often yielding stronger downstream model performance, particularly for low-resource languages.

Jan Cegin, Daniil Gurgurov, Yusser Al Ghussin +1

Kempelen Institute of Intelligent Technologies, Bratislava, Slovakia · German Research Institute for Artificial Intelligence (DFKI), Saarbrücken, Germany

Language Model Steering Synthetic Data Generation for Language Models Low-Resource Language Processing Activation Steering Large Language Model-Based Data Augmentation

Jun 15, 2026

SPARK: Security Knowledge Priming and Representation-Guided Knowledge Activation for LLM-based Secure Code Generation

Large language models routinely generate code with exploitable security flaws. Prior literature attributes this limitation to a lack of security expertise, steering current defense mechanisms toward heavy fine-tuning or external knowledge retrieval, which introduces significant computational overhead and data bias through redundant code examples. Contrary to this view, we argue that pretraining corpora are already rich in security material. The bottleneck is activation: without an explicit and brief cue, statistical pressure toward common training-distribution patterns suppresses the model's safety-relevant representations. We present SPARK, an inference-time security harness that activates this latent knowledge without any retraining. The harness has two parts. ComponentI retrieves a few of the relevant Common Weakness Enumeration (CWE) entries for each coding task and appends a short structured cue to the prompt; this alone is enough to surface the model's existing security representations. ComponentII adds a precomputed token bias to the logits at every decoding step. We obtain the bias by projecting a safe-direction vector, the unit difference between the mean safe and mean unsafe last-layer hidden states, through the language model head. The bias is computed once offline; applying it costs a single vector addition per generated token. We evaluate SPARK on 9 open-source models across C++, Java, and Python, and compare with 7 baselines spanning fine-tuning and retrieval-augmented methods. SPARK matches or improves on the best baseline in every setting while preserving HumanEval utility. We further test Component~I in a black-box setting on 7 of today's strongest models, including Claude, DeepSeek, and GPT, demonstrating the bottleneck of insecure code generation and the improvements enabled by our method.

Xiaoyun Xu, Lichao Wu, Jona te Lintelo +2

Radboud University · University of Bristol · University of Zagreb

Knowledge Augmentation for Language Models LLM Security Secure Code Generation Activation Steering

Jun 13, 2026

High-Dimensional Random Projection for Activation Steering in Language Models

Activation steering has emerged as a key methodology for controlling the behavior of large language models (LLMs). Existing difference-in-means based methods, however, are fundamentally limited: they capture only mean differences between class activations and fail to recover discriminative signals that naturally exist in the nonlinear feature subspace under the superposition hypothesis. Motivated by that, we propose High-Dimensional Random-projection for Activation Steering (HiDRA), a training-free approach that integrates seamlessly with existing activation steering methods. By performing activation addition in the projected high-dimensional space, HiDRA can provably capture a better discriminative structure beyond the reach of linear methods. Experiments across diverse LLM families and benchmarks demonstrate that HiDRA consistently outperforms baseline counterparts, achieving stronger behavioral control without significant computational overhead.

Minh-Hieu Pham, Bach Do, Laziz Abdullaev +2

Hanoi University of Science and Technology

Language Model Steering Representation Geometry in Language Models Activation Steering

Jun 11, 2026

Improving Robotic Generalist Policies via Flow Reversal Steering

Generalist policies can learn a wide range of skills from diverse robot datasets. In order to solve or improve on challenging new tasks, we need a way to infer and invoke the appropriate actions from the policy's rich behavioral prior, especially when directly commanding the policy fails. We focus on flow matching generalists and propose Flow Reversal Steering (FRS): a method that takes suboptimal but ``reasonable'' actions, finds their latent noises by passing them through the flow policy in reverse, and maps them to nearby generalist action modes. We evaluate FRS across many simulated and real-world manipulation settings. First, FRS can turn coarse semantic guidance from humans or vision-language models (VLMs) into corresponding good robot actions, improving zero-shot control. These gains can be distilled with behavioral cloning by training an auxiliary policy to output noises that the generalist maps to good actions -- showing up to 95% absolute task success rate boosts in under a minute of training. Finally, FRS enables policy improvement by bootstrapping reinforcement learning with semantic knowledge, improving on several tasks that standard RL fails to improve on.

Andy Tang, William Chen, Andrew Wagenmaker +2

Stanford University · UC Berkeley

RL for Robotics Robot Policy Learning Robot Skill Learning Generalization in Robotic Manipulation Robotic Manipulation Activation Steering

Jun 11, 2026

Refusal Beyond a Single Direction: A Preliminary Comparison of Diff-in-Means and INLP

Arditi et al. (2024) has shown that refusal in safety fine-tuned chat models is mediated by a single linear direction in the residual stream, recoverable by a difference-in-means (DiM) of harmful and harmless activations. We compare DiM-based interventions (activation addition and directional ablation) with two interventions derived from Iterative Nullspace Projection (INLP)-nullspace projection and counterfactual flipping-on five open-weight chat models, asking whether INLP can match DiM at steering refusal and whether its richer parameterisation yields more tweakable interventions. INLP counterfactual flipping is competitive with DiM directional ablation on refusal suppression, while nullspace projection is weaker on most models. Applying each method at the layer selected by the other shows that flipping's competitiveness is robust to this change while directional ablation's is not, suggesting that DiM's apparent edge is partly a property of its own selection procedure. Restricting INLP to the leading directions of the extracted subspace preserves most of the suppression effect at near-baseline perplexity, giving a tunable capability. Geometrically, the two INLP interventions land in qualitatively different regions of activation space: nullspace projection collapses transformed activations between the harmful and harmless clusters, while counterfactual flipping moves them into the opposite cluster, suggesting that the model encodes the absence of a concept differently from its opposit--an intriguing distinction that warrants further investigation in future work.

Elisabetta Rocchetti, Alfio Ferrara

Department of Computer Science, Università degli Studi di Milano, Milan, Italy · Department of Literary Studies, Philology and Linguistics, Università degli Studi di Milano, Milan, Italy

LLM Refusal Behavior Causal Interventions in Language Models Refusal Behavior in Language Models Activation Steering Refusal Mechanisms in Language Models

Jun 10, 2026

The Signs Were Always There: Training-Free Detection and Control in Raw Transformer Dimensions

Because of polysemanticity and superposition, it has been challenging to attribute token understanding and generation to specific neurons or dimensions. Yet the information in the hidden states is so rich that the signs of the residual stream can surface semantic content in early layers and control what the model generates. We call this sign-pattern-driven interpretation approach Bag of Dims (BoD). Using BoD, we read each dimension of the residual stream individually. Since dimensions carry almost no shared information, a concept is simply the set of dimensions that agree in sign. This lets us discover tens to hundreds of thousands of concepts per model without training or labels. A concept is detectable as early as the first few layers, at AUC above 0.9 across the model families we tested, well before the answer it resolves to becomes legible. BoD can therefore screen harmful prompts at prefill, without a trained guard model. The prediction capability of the signs is strong: setting all magnitudes to unity preserves 56-94% top-5 next-token accuracy through the language model head. Flipping a concept's sign pattern during the forward pass suppresses its logits, and a separate training-free intervention steers a chosen concept into generated text. The BoD method depends on the transformers' per-dimension sign pattern, present across the residual stream, attention, and MLP subspaces, rather than on any particular architecture, making it applicable to a wide range of models.

Varun Reddy Nalagatla, Madhavi Evana, Yiwen Zhang

Amazon Web Services

Transformer Interpretability Representation Engineering Activation Steering

Jun 10, 2026

On The Effectiveness-Fluency Trade-Off In LLM Conditioning: A Systematic Study

Controlling the output of Large Language Models (LLMs) is a central challenge for their reliable deployment, yet a clear understanding of the involved trade-offs remains elusive. Current approaches to conditioning are often evaluated with a narrow focus on their effectiveness at injecting or removing a target concept, neglecting generation quality. We systematically investigate a range of conditioning methods in both injection and removal scenarios. We find that efficient steering methods frequently achieve conditioning at a steep cost to fluency. Furthermore, we identify a critical yet previously overlooked interaction with the training paradigm: activation steering methods are far less effective on instruction-tuned models than on their base counterparts. Simple prompting and full-fledged supervised fine-tuning, on the other hand, are viable options for concept injection, but are not as good at concept removal. Finally, cheaply computed textual metrics highly correlate to costly LLM-as-judge scores, and provide insights on the behavior of conditioning methods.

Iuri Macocco, Pau Rodríguez, Arno Blaas +3

Universitat Pompeu Fabra · Apple · Universitat Pompeu Fabra / ICREA

LLM Fine-Tuning Activation Steering Concept Erasure

Jun 9, 2026

Steering Multirobot Behavior via Closed-Loop Affine Activation Editing

Real-world robots need to adapt their behavior beyond the envelope of their pre-trained policy. Policy finetuning or retraining are options, but they risk catastrophic forgetting, degrading the pretrained policy's base performance. To combat this, we introduce CLAE: Closed-Loop Affine Activation Editing, an inference-time framework for steering the behavior of a frozen policy by editing intermediate activations while keeping the base policy weights and downstream action head untouched. CLAE approaches behavior steering as a closed-loop problem whose outputs edit policy activations that adapt online to the robot state, environment, target behavior, and multi-robot context. It trains a sparse autoencoder over frozen-policy activations, selects behavior-relevant latent features via post-hoc probing, and learns a lightweight RL-based steering policy that applies state-dependent affine edits to selected latents during inference. We validate CLAE on a frozen multi-quadrotor navigation policy trained to perform a single task: navigating robots to a set of goal locations while avoiding obstacles. Through extensive simulations and physical tests, we show that while navigating to their goal positions, CLAE can 1. steer individual robot behavior by controlling each robot's velocity profile; 2. coordinate multirobot behavior by preserving a desired formation; and 3. produce entirely new behavior wherein robots are required to reduce their exposure to surveillance cameras in the environment. Our project website is available at https://clae-robotics.github.io/.

Satyajeet Das, Darren Chiu, Shashank Hegde +1

Department of Computer Science University of Southern California Los Angeles, CA, USA

Robot Policy Learning Robot Policy Adaptation Multi-Robot Coordination Activation Steering

Jun 9, 2026

Scenario-based Probing and Steering Cultural Values in Large Language Models--Extended Version

Large Language Models (LLMs) are deployed across cultural contexts but often reflect homogenized values inherited from training data. Evaluations of cultural alignment typically rely on direct prompting with survey-style questions, which frequently elicit neutral or safety-aligned responses and fail to capture underlying model preferences. We propose a framework for probing and steering latent cultural representations in LLMs along the two Inglehart--Welzel axes of the World Values Survey (WVS). By translating social value questions into scenario-based behavioral dilemmas, we extract token-level probabilities to measure implicit values and apply activation steering, optionally combined with country-conditioned prompting, to shift model behavior without retraining. Across three open-source LLMs and four target cultures, we find substantial variation in steerability and identify latent entanglement, where interventions along one cultural dimension induce shifts along another. This coupling mirrors correlations in human WVS data and persists across activation, prompt, and hybrid steering. It constrains axis-independent alignment, though general task performance is largely preserved.

Trung Duc Anh Dang, Tung Kieu, Sarah Masud

University of Copenhagen · Aalborg University

Language Model Steering Cultural Alignment Cultural Bias in Language Models Activation Steering Language Model Probing

Jun 9, 2026

Overcoming State Inertia in Full-Duplex Spoken Language Models via Activation Steering

Full-duplex spoken language models (FD-SLMs) enable seamless speech interaction by allowing models to listen and speak simultaneously, yet the internal mechanism by which they coordinate listening and speaking remains underexplored. We analyze the predictive behavior encoded in FD-SLM hidden representations and find that they exhibit stream-specific predictive patterns: during listening, they preferentially predict the incoming user stream, whereas during speaking, they preferentially predict the model output stream. Building on this observation, we show that FD-SLMs dynamically modulate their internal predictive focus between two states: a generative state aligned with model output generation and a perceptive state aligned with incoming user input. However, this modulation can lag behind abrupt changes in conversational context. During user interruptions, the model remains transiently biased toward the generative state before transitioning into the perceptive state, causing it to miss the beginning of the incoming input. We term this delayed internal transition state inertia. To quantify its downstream impact, we introduce the Zero-Buffer Benchmark (ZBB), a diagnostic benchmark for evaluating immediate interruption comprehension when user speech begins abruptly. We evaluate this setting using response correctness and initial-word occurrence rate (IWOR). Finally, we mitigate state inertia through activation steering with a perception vector, a training-free intervention with little additional computational overhead. Across multiple state-of-the-art FD-SLMs, activation steering substantially improves interruption handling; for example, on PersonaPlex, it improves correctness from 28% to 45% and IWOR from 40% to 72% without any fine-tuning.

Cheng-Kuang Chang, Kai-Wei Chang, Alexander H. Liu +1

MIT CSAIL

Language Model Steering Spoken Dialogue Systems Speech Language Models Activation Steering Full-Duplex Spoken Dialogue Systems

Jun 9, 2026

Recoverable but Not Stationary:Local Linear Structures in Weights and Activations

Task vectors, LoRA, activation steering, and random search around pretrained weights all suggest that learned behaviour can be controlled by linear directions. We ask which linear structures actually exist and on what scale. In a synthetic multitask transformer and LoRA adapters on DistilGPT-2 / GPT-2 we find strong local low-rank task-gradient structure but reject the fixed-task-plane hypothesis: static bases miss the recovery direction, and the useful basis drifts substantially within 100 steps. However, the first recovery updates form a trajectory-prefix basis capturing 77% of the LoRA recovery displacement. We develop random search theory with a Gaussian local-linear theorem that justifies the effectiveness of random parameter search even in very high dimensions. We also study the relation between parameter perturbations and activation steering: a single gradient step produces an activation shift with 0.58 cosine to a labelled-contrast CAA steering vector, with a similar steering effect on Qwen-0.5B BoolQ statements. We validate our results with experiments on synthetic Transformers and LLMs. Our results suggest that linear structures in trained networks are not global task directions, but evolving local geometries that partially persist across parameter and activation spaces.

Irina Piontkovskaia, Sergey Nikolenko

St. Petersburg Department of the Steklov Institute of Mathematics, St. Petersburg, Russia · St. Petersburg State University

Low-Rank Adaptation Activation Steering

Jun 7, 2026

The Amplifying Mirror: Locating and Steering the Partisan Direction inside a Large Language Model

Large language models are rapicly replacing search engines as the primary interface between people and information. Unlike search engines, which retrieve existing content, LLMs generate novel text shaped by internal representations learned during training. Here we show that partisan political identity is encoded in the model's activation space, and that this direction directly shapes generation. Using 190,491 tweets from sitting members of the U.S. Congress as labeled training data, we train linear probes on the hidden states of the Llama 3.1 8B Instruct model. We identify a single geometric axis at layer 18 that separates Republican from Democratic text with an AUC of 0.945 and a Cohen's d of 1.94, and use sparse autoencoders to decompose that axis into interpretable partisan features. Causally intervening along this axis, ablating or amplifying the partisan component mid-generation, produces systematic shifts in the model's output. We witness stance reversals, register shifting, and structured fabrications of authority. Our results demonstrate that partisan bias in language models is not a vague emergent property but a learned geometric feature that can be precisely located and steered. Partisan bias is not a bug to be patched, but a structural property of how these models encode information about their users. As LLMs displace search engines as the interface to knowledge, understanding that product design (and its consequences) will be essential for navigating the legal, social, and political transitions from an information ecosystem that is curated to one that is generated.

Wendy K. Tam

Professor and Stevenson Chair in the Departments of Political Science, Computer Science, Biomedical Informatics, and the Law School at Vanderbilt University

LLM Interpretability Political Bias in Language Models Linguistic Bias in Language Models Causal Interventions in Language Models Activation Steering

Jun 7, 2026

Activation Steering Induces Emergent Misalignment: Steering Vector Construction and Comprehensive Evaluation

Activation steering (AS) has emerged as a popular inference-time technique for modulating the behavior of large language models (LLMs). AS modulates model behavior in a flexible and lightweight manner by injecting task-specific steering vectors (SVs) into intermediate activations. Meanwhile, recent work has identified emergent misalignment (EM) as an emerging safety concern, whereby finetuning on unsafe examples from a narrow task unexpectedly induces broadly unsafe behavior in unrelated domains. With the increasing popularity of AS, it is pressing yet under-explored to thoroughly investigate whether AS can induce EM. In this paper, we conduct a comprehensive study of activation-steering-induced emergent misalignment. Specifically, (1) we identify a steering vector construction to confirm that SVs derived from a narrow task can indeed induce misalignment across broad unrelated domains. Qualitative measurement further reveals that AS-induced EM may pose more severe safety risks than finetuning-induced EM, i.e., AS elicits more actionable harmful responses with greater semantic coherence than those generated by finetuned models. (2) We characterize the properties of AS-induced EM by analyzing key steering-specific factors, including steering magnitude, the low-rank structure of the steering subspace, and the number of fine-tuning epochs used during steering-vector construction. (3) We evaluate the robustness and sensitivity of AS-induced EM across diverse model families, model scales, target tasks, and intervention layers. Our findings reveal activation steering as a significant yet underexamined source of emergent misalignment and provide an activation-space perspective on emergent misalignment and its safety risks.

Qi Cao, Jian Lou, Meiting Liu +3

Nanyang Technological University · Sun Yat-sen University · University of Science and Technology of China

Language Model Safety Evaluation LLM Safety Emergent Misalignment Activation Steering

Jun 7, 2026

Beyond Linear Activation Steering: Invertible Latent Transformations for Controlling LLM Behavior

Activation steering provides a lightweight inference-time mechanism for controlling large language models (LLMs) by modifying their internal activation vectors toward desired behaviors. Most existing methods compute a fixed steering direction in the original activation space, typically from pairs of contrastive examples using mean differences, linear probes, or arbitrary separability criteria. While effective to a certain extent, these methods treat behavioral control as a global, linear, additive offset: the same direction is applied across inputs, and behaviors are linearly separable. This can be restrictive when behavioral features vary nonlinearly across the activation space or lie on curved and anisotropic manifolds, where the optimal intervention may be input-dependent. To address this limitation, we propose INNSteer, a nonlinear activation steering framework based on invertible latent transformations. Rather than searching for a better steering vector in the original representation space, INNSteer learns a lightweight invertible neural network

φ

that maps an LLM's activations into a latent space where behavioral classes are more amenable to linear control. At inference time, activations are mapped through

φ

, steered in the latent space, and mapped back through the exact inverse transformation

φ^{-1}

. This makes a simple latent-space translation become a nonlinear, input-dependent intervention in the original activation space. Across experiment settings on multiple LLM families, scales, behavioral traits, and safety benchmarks, INNSteer consistently improves model control over linear, transport-based, and nonlinear steering baselines while largely preserving generation fluency.

Tuc Nguyen, Thai Le

Indiana University Bloomington, USA

Invertible Neural Networks Language Model Steering Activation Steering

Jun 7, 2026

TimpaTeks: Automatic In-place Text Sequence Modification via Diffusion Language Model Steering

We extend activation steering to diffusion language models (DLMs) and study a novel problem that arose due to the inference mechanism of DLMs: Modifying a text in-place to manifest a different concept. We propose TimpaTeks, an automatic in-place text modification mechanism using DLMs. Experiments on IMDB movie reviews (sentiment) and a synthetic Cats and Dogs Dataset (arbitrary, more unconventional concept steering) show that TimpaTeks provides a feasible novel mechanism to steer diffusion language model outputs in-place. TimpaTeks enables in-place modification while simultaneously lowers sentence perplexity and retaining the original sentence structre without the need of instruction tuned models. TimpaTeks is also computationally cheaper than prompt-based DLM steering, as it performs denoising in-place rather than constructing an additional prompt-conditioned output sequence.

Ryandito Diandaru, Ahmed Elshabrawy, Fadli Aulawi Al Ghiffari +2

MBZUAI

Language Model Steering Diffusion Language Models Activation Steering Text Generation

Jun 5, 2026

TALAN: Task-Aligned Latent Adaptation Networks for Targeted Post-Training of Large Language Models

Targeted post-training aims to improve reasoning, math, and code without degrading strengths. Low-rank adapters are efficient but task-global; activation interventions are input-aware but often require separate probes, vectors, or inference-time steering. We introduce TALAN (Task-Aligned Latent Adaptation Networks), a sequence-conditioned latent side path inserted into a transformer's residual stream and co-trained with a low-rank adapter in one SFT loop. TALAN compresses the active sequence into latent memory, remixes it into token-level perturbations, and writes them back through a controlled residual update. It is configured along six axes: insertion location, memory size, mixer, writeback rule, trainability scope, and gradient scale. Across four Qwen3-family backbones and four STEM/code benchmarks, TALAN improves matched LoRA and DoRA baselines. With LoRA, it yields a +1.41 point cross-model mean gain, positive on all four backbones and non-negative on all 16 model-benchmark cells. With DoRA, it yields a +1.85 point mean gain, positive on all backbones and on 13 of 16 cells. Paired seed checks support positive average effects but show nontrivial variance, so we treat them as sensitivity checks. Cost is small: <1% trainable parameters relative to the backbone and 1.01-1.02x inference overhead versus matched LoRA. A Llama-3.2-1B transfer probe is also positive under LoRA and rsLoRA across seven paired seeds, supporting a transfer beyond Qwen. Internal-state analyses suggest TALAN is a small complementary activation intervention. The matched adapter update is 80-1,700x larger than the TALAN perturbation, yet their directions have near-zero cosine; per-layer measurements show this small orthogonal perturbation propagates and amplifies through depth. TALAN offers a practical platform for studying steerable activation-level adaptation within standard adapter-based post-training.

Chengkai Zhang, Ziteng Liu, Junpu Wang +4

Meta AI

Supervised Fine-Tuning Adapter Tuning Low-Rank Adaptation LLM Post-Training Activation Steering LLM Reasoning