Activation Steering

Ask about this topic

Overview

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

CardsList

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

Mar 17, 2026

Parametric Social Identity Injection and Diversification in Public Opinion Simulation

Large language models (LLMs) have recently been adopted as synthetic agents for public opinion simulation, offering a promising alternative to costly and slow human surveys. Despite their scalability, current LLM-based simulation methods fail to capture social diversity, producing flattened inter-group differences and overly homogeneous responses across demographic groups. We identify this limitation as a Diversity Collapse phenomenon in LLM hidden representations, where distinct social identities become increasingly indistinguishable across layers. Motivated by this observation, we propose Parametric Social Identity Injection (PSII), a general framework that injects explicit, parametric representations of demographic attributes and value orientations directly into intermediate hidden states of LLMs. Unlike prompt-based persona conditioning, PSII enables fine-grained and controllable identity modulation at the representation level. Extensive experiments on the World Values Survey using multiple open-source LLMs show that PSII significantly improves distributional fidelity and diversity, reducing KL divergence to real-world survey data while enhancing overall diversity. This work provides new insights into representation-level control of LLM agents and advances scalable, diversity-aware public opinion simulation.

Hexi Wang, Yujia Zhou, Bangde Du +2

DCST, Tsinghua University Beijing, China · Quancheng Laboratory Jinan, Shandong, China

Large Language Model-Based Social SimulationRepresentation Geometry in Language ModelsActivation Steering
AskPDF
Mar 12, 2026

Efficient Reasoning with Balanced Thinking

Large Reasoning Models (LRMs) have shown remarkable reasoning capabilities, yet they often suffer from overthinking, expending redundant computational steps on simple problems, or underthinking, failing to explore sufficient reasoning paths despite inherent capabilities. These issues lead to inefficiencies and potential inaccuracies, limiting practical deployment in resource-constrained settings. Existing methods to mitigate overthinking, such as suppressing reflective keywords or adjusting reasoning length, may inadvertently induce underthinking, compromising accuracy. Therefore, we propose ReBalance, a training-free framework that achieves efficient reasoning with balanced thinking. ReBalance leverages confidence as a continuous indicator of reasoning dynamics, identifying overthinking through high confidence variance and underthinking via consistent overconfidence. By aggregating hidden states from a small-scale dataset into reasoning mode prototypes, we compute a steering vector to guide LRMs' reasoning trajectories. A dynamic control function modulates this vector's strength and direction based on real-time confidence, pruning redundancy during overthinking, and promoting exploration during underthinking. Extensive experiments conducted on four models ranging from 0.5B to 32B, and across nine benchmarks in math reasoning, general question answering, and coding tasks demonstrate that ReBalance effectively reduces output redundancy while improving accuracy, offering a general, training-free, and plug-and-play strategy for efficient and robust LRM deployment. Project page and code are available at https://rebalance-ai.github.io .

Yulin Li, Tengyao Tu, Li Ding +5

Harbin Institute of Technology (Shenzhen) · Zhongguancun Academy · Huawei Noah’s Ark Lab +3

Efficient Language Model ReasoningLarge Reasoning ModelsOverthinking in Language ModelsActivation Steering
AskPDF
Mar 12, 2026

Global Evolutionary Steering: Refining Activation Steering Control via Cross-Layer Consistency

Activation engineering enables precise control over Large Language Models (LLMs) without the computational cost of fine-tuning. However, existing methods deriving vectors from static activation differences are susceptible to high-dimensional noise and layer-wise semantic drift, often capturing spurious correlations rather than the target intent. To address this, we propose Global Evolutionary Refined Steering (GER-steer), a training-free framework that grounded in the geometric stability of the network's representation evolution. GER-steer exploits this global signal to rectify raw steering vectors, effectively decoupling robust semantic intent from orthogonal artifacts. Extensive evaluations confirm that GER-steer consistently outperforms baselines, delivering superior efficacy and generalization without layer-specific tuning, establishing a universal solution for reliable model alignment.

Xinyan Jiang, Wenjing Yu, Di Wang +1

Mohamed bin Zayed University of Artificial Intelligence (MBZUAI) · Provable Responsible AI and Data Analytics (PRADA) Lab · King Abdullah University of Science and Technology +3

Language Model SteeringActivation SteeringLLM Alignment
AskPDF
Mar 11, 2026

Security-by-Design for LLM-Based Code Generation: Leveraging Internal Representations for Concept-Driven Steering Mechanisms

Large Language Models (LLMs) show remarkable capabilities in understanding natural language and generating complex code. However, as practitioners adopt CodeLLMs for increasingly critical development tasks, research reveals that these models frequently generate functionally correct yet insecure code, posing significant security risks. While multiple approaches have been proposed to improve security in AI-based code generation, combined benchmarks show these methods remain insufficient for practical use, achieving only limited improvements in both functional correctness and security. This stems from a fundamental gap in understanding the internal mechanisms of code generation and the root causes of security vulnerabilities, forcing researchers to rely on heuristics and empirical observations. In this work, we investigate the internal representation of security concepts in CodeLLMs, revealing that models are often aware of vulnerabilities as they generate insecure code. Through systematic evaluation, we demonstrate that CodeLLMs can distinguish between security subconcepts, enabling a more fine-grained analysis than prior black-box approaches. Leveraging these insights, we propose Secure Concept Steering for CodeLLMs (SCS-Code). During token generation, SCS-Code steers LLMs' internal representations toward secure and functional code output, enabling a lightweight and modular mechanism that can be integrated into existing code models. Our approach achieves superior performance compared to state-of-the-art methods across multiple secure coding benchmarks.

Maximilian Wendlinger, Daniel Kowatsch, Konstantin Böttinger +1

Cognitive Security Technologies Fraunhofer Institute for Applied and Integrated Security Garching near Munich, Germany

Secure Code GenerationCode Language ModelsLLM Code GenerationLLM SecurityActivation Steering
AskPDF
Mar 11, 2026

PRISM-ΔΔ: Differential Subspace Steering for Prompt Highlighting in Large Language Models

Prompt highlighting steers a large language model to prioritize user-specified text spans during generation. A key challenge of existing Key-editing approaches is extracting steering directions that capture the difference between relevant and irrelevant contexts, rather than shared structural patterns common to both. We propose PRISM-ΔΔ (Projection-based Relevance-Informed Steering Method), which decomposes the difference between positive and negative cross-covariance matrices to maximize discriminative energy while eliminating shared directions. Each attention head receives a continuous softplus importance weight, letting weak-but-useful heads contribute at reduced strength. The framework extends naturally to Value representations, capturing content-channel signal that Key-only methods leave unused. Across four benchmarks and five models, our methods match or exceed the best existing method on 19 of 20 configurations, with relative gains up to +13.0%, while halving the fluency cost of steering. Our methods also scale to long-context retrieval, outperforming the best existing method by up to +5.1% relative gain. PRISM-ΔΔ is compatible with FlashAttention and adds negligible memory overhead.

Yuyao Ge, Shenghua Liu, Yiwei Wang +5

♣Institute of Computing Technology, Chinese Academy of Sciences · △University of California, Merced

Language Model SteeringLLM PromptingActivation Steering
AskPDF
Mar 10, 2026

Adaptive Activation Cancellation for Hallucination Mitigation in Large Language Models

Large Language Models frequently generate fluent but factually incorrect text. We propose Adaptive Activation Cancellation (AAC), a real-time inference-time framework that treats hallucination-associated neural activations as structured interference within the transformer residual stream, drawing an explicit analogy to classical adaptive noise cancellation from signal processing. The framework identifies Hallucination Nodes (H-Nodes) via layer-wise linear probing and suppresses them using a confidence-weighted forward hook during auto-regressive generation -- requiring no external knowledge, no fine-tuning, and no additional inference passes. Evaluated across OPT-125M, Phi-3-mini, and LLaMA 3-8B on TruthfulQA and HaluEval, the real-time hook is the only intervention that consistently improves downstream accuracy on all three scales. Critically, the method is strictly surgical: WikiText-103 perplexity and MMLU reasoning accuracy are preserved at exactly 0.0% degradation across all three model scales, a property that distinguishes AAC from interventions that trade fluency or general capability for factual improvement. On the LLaMA 3-8B scale, the hook additionally yields positive generation-level gains (MC1 +0.04; MC2 +0.003; Token-F1 +0.003) while achieving probe-space selectivity 5.94x - 3.5x higher than the ITI baseline -- demonstrating that targeted neuron-level suppression can simultaneously improve factual accuracy and preserve model capability.

Eric Yocam, Varghese Vaidyan, Gurcan Comert +3

The Beacom College of Computer and Cyber Sciences, Dakota State University, Madison, SD 57042, USA. · Department of Computational Data Science and Engineering, North Carolina A&T State University, Greensboro, NC 27411, USA. · Department of Computer Science and Software Engineering, California Polytechnic State University, San Luis Obispo, CA 93407, USA. +2

LLM Hallucination MitigationActivation Steering
AskPDF
Mar 10, 2026

Amnesia: Adversarial Semantic Layer Specific Activation Steering in Large Language Models

Warning: This article includes red-teaming experiments, which contain examples of compromised LLM responses that may be offensive or upsetting. Large Language Models (LLMs) have the potential to create harmful content, such as generating sophisticated phishing emails and assisting in writing code of harmful computer viruses. Thus, it is crucial to ensure their safe and responsible response generation. To reduce the risk of generating harmful or irresponsible content, researchers have developed techniques such as reinforcement learning with human feedback to align LLM's outputs with human values and preferences. However, it is still undetermined whether such measures are sufficient to prevent LLMs from generating interesting responses. In this study, we propose Amnesia, a lightweight activation-space adversarial attack that manipulates internal transformer states to bypass existing safety mechanisms in open-weight LLMs. Through experimental analysis on state-of-the-art, open-weight LLMs, we demonstrate that our attack effectively circumvents existing safeguards, enabling the generation of harmful content without the need for any fine-tuning or additional training. Our experiments on benchmark datasets show that the proposed attack can induce various antisocial behaviors in LLMs. These findings highlight the urgent need for more robust security measures in open-weight LLMs and underscore the importance of continued research to prevent their potential misuse.

Ali Raza, Gurang Gupta, Nikolay Matyunin +1

Honda Research Institute Europe Offenbach, Hesse, Germany · IIT KharagPur Kharagpur, India

Adversarial Attacks on LLMsLLM Jailbreak AttacksLLM SafetyActivation Steering
AskPDF
Mar 10, 2026

Curveball Steering: The Right Direction To Steer Isn't Always Linear

Activation steering is a widely used approach for controlling large language model (LLM) behavior by intervening on internal representations. Existing methods largely rely on the Linear Representation Hypothesis, assuming behavioral attributes can be manipulated using global linear directions. In practice, however, such linear interventions often behave inconsistently. We question this assumption by analyzing the intrinsic geometry of LLM activation spaces. Measuring geometric distortion via the ratio of geodesic to Euclidean distances, we observe substantial and concept-dependent distortions, indicating that activation spaces are not well-approximated by a globally linear geometry. Motivated by this, we propose "Curveball steering", a nonlinear steering method based on polynomial kernel PCA that performs interventions in a feature space, better respecting the learned activation geometry. Curveball steering consistently outperforms linear PCA-based steering, particularly in regimes exhibiting strong geometric distortion, suggesting that geometry-aware, nonlinear steering provides a principled alternative to global, linear interventions.

Shivam Raval, Hae Jin Song, Linlin Wu +4

Language Model SteeringActivation SteeringRepresentation Geometry in Language ModelsPrincipal Component Analysis
AskPDF
Mar 7, 2026

PolypSteer: Counterfactual Endoscopic Synthesis via Training-Free Activation Steering

Generative diffusion models are increasingly used for medical imaging data augmentation, but text prompting cannot produce causal training data. Re-prompting rerolls the entire generation trajectory, altering anatomy, texture, and background. Inversion-based editing methods introduce reconstruction error that causes structural drift. We propose PolypSteer, a training-free activation-steering framework for endoscopic synthesis. PolypSteer identifies a pathology vector for each contrastive prompt pair in the cross-attention layers of a diffusion transformer. At inference time, it steers image activations along this vector, generating counterfactual pairs from scratch where the only difference is the steered concept. All other structure is preserved by construction. We evaluate PolypSteer across three experiments on Kvasir v3 and HyperKvasir. On counterfactual generation across three clinical concept pairs, PolypSteer achieves flip rates of 0.800, 0.925, and 0.950, outperforming the best inversion-based baseline in both concept flip rate and structural preservation. On dye disentanglement, PolypSteer achieves 75% dye removal against 20% (PnP) and 10% (h-Edit). On downstream polyp detection, augmenting with PolypSteer counterfactual pairs achieves ViT AUC of 0.9755 versus 0.9083 for quantity-matched re-prompting, confirming that counterfactual structure drives the gain. Code is at link https://github.com/UARK-AICV/PolypSteer

Trong-Thang Pham, Loc Nguyen, Anh Nguyen +2

University of Arkansas, Fayetteville AR, USA · University of Liverpool, Liverpool, UK · University of Houston, Houston TX, USA

Counterfactual Image GenerationMedical Image SynthesisCounterfactual Data AugmentationImage GenerationEndoscopyActivation Steering
AskPDF
Mar 6, 2026

COLD-Steer: Steering Large Language Models via In-Context One-step Learning Dynamics

Activation steering methods enable inference-time control of large language model (LLM) behavior without retraining, but current approaches face a fundamental trade-off: sample-efficient methods suboptimally capture steering signals from labeled examples, while methods that better extract these signals require hundreds to thousands of examples. We introduce COLD-Steer, a training-free framework that steers LLM activations by approximating the representational changes that would result from gradient descent on in-context examples. Our key insight is that the effect of fine-tuning on a small set of examples can be efficiently approximated at inference time without actual parameter updates. We formalize this through two complementary approaches: (i) a unit kernel approximation method that updates the activations directly using gradients with respect to them, normalized across examples, and (ii) a finite-difference approximation requiring only two forward passes regardless of example count. Experiments across a variety of steering tasks and benchmarks demonstrate that COLD-Steer achieves upto 95% steering effectiveness while using 50 times fewer samples compared to the best baseline. COLD-Steer facilitates accommodating diverse perspectives without extensive demonstration data, which we validate through our experiments on pluralistic alignment tasks. Our framework opens new possibilities for adaptive, context-aware model control that can flexibly address varying loss-driven human preferences through principled approximation of learning dynamics rather than specialized training procedures.

Kartik Sharma, Rakshit S. Trivedi

Georgia Institute of Technology · Massachusetts Institute of Technology

Language Model SteeringInference-Time Language Model AlignmentActivation Steering
AskPDF
Mar 6, 2026

Enhancing Instruction Following of LLMs via Activation Steering with Dynamic Rejection

Large Language Models (LLMs), despite advances in instruction tuning, often fail to follow complex user instructions. Activation steering techniques aim to mitigate this by manipulating model internals, but have a potential risk of oversteering, where excessive emphasis on the instruction degrades task accuracy and overall text quality. To address this, we introduce DIRECTER (Dynamic rejection steering), a novel steering method that dynamically modulates steering strength by scaling the KV cache without extra dataset. DIRECTER couples steering with a plausibility-guided decoding loop, which adaptively adjusts steering strength at each step by comparing the steered output distribution to the original. If the steered output is deemed implausible, steering strength is progressively weakened. This strength modulation is guided by a lightweight, one-time attention sensitivity analysis that ranks layers by their influence on model representations. Extensive evaluations show that DIRECTER significantly enhances instruction-following capabilities across diverse benchmarks, improving accuracy by up to 6.5% over baselines without the common trade-offs in generation quality or task fidelity. The proposed dynamic, plausibility-guided control during activation steering further demonstrates its potential as a general mechanism for mitigating oversteering that is compatible with existing baselines.

Minjae Kang, Jaehyung Kim

Yonsei University

Language Model SteeringInstruction FollowingActivation SteeringLanguage Model Decoding
AskPDF
Mar 5, 2026

Observing and Controlling Features in Vision-Language-Action Models

Vision-Language-Action models (VLAs) have shown remarkable progress towards embodied intelligence. While their architecture partially resembles that of Large Language Models (LLMs), VLAs exhibit higher complexity due to their multi-modal inputs/outputs and often hybrid nature of transformer and diffusion heads. This is part of the reason why insights from mechanistic interpretability in LLMs, which explain how the internal model representations relate to their output behavior, do not trivially transfer to VLA counterparts. In this work, we investigate whether VLA internal representations support lightweight behavioral steering without retraining. Across four frontier VLA models, linear observers recover state- and action-relevant information in both autoregressive and transformer--flow-matching architectures, and provide robust directions to causally alter VLA outputs. Building on this, we introduce a controller that minimally modifies representations to place observer predictions within prescribed target intervals. Closed-loop experiments with π0.5π_{0.5} in the LIBERO simulator and on DROID hardware demonstrate improved constraint satisfaction while retaining task performance, with only approximately 1%1\% inference overhead. Together, these experiments show that lightweight linear interventions can reliably steer VLA behavior while preserving closed-loop capabilities, enabling alignment with user preferences and task requirements without fine-tuning.

Hugo Buurmeijer, Carmen Amo Alonso, Aiden Swann +1

Dept. of Aeronautics and Astronautics, Stanford University · Dept. of Mechanical Engineering, Stanford University · NVIDIA Research

VLM InterpretabilityVision-Language-Action ModelsVLMs for RoboticsActivation Steering
AskPDF
Mar 4, 2026

Stable and Steerable Sparse Autoencoders with Weight Regularization

Sparse autoencoders (SAEs) are widely used to extract human-interpretable features from neural network activations, but their learned features can vary substantially across random seeds and training choices. To improve stability, we studied weight regularization by adding L1 or L2 penalties on encoder and decoder weights, and evaluate how regularization interacts with common SAE training defaults. On MNIST, we observe that L2 weight regularization produces a core of highly aligned features and, when combined with tied initialization and unit-norm decoder constraints, it dramatically increases cross-seed feature consistency. For TopK SAEs trained on language model activations (Pythia-70M-deduped), adding a small L2 weight penalty increased the fraction of features shared across three random seeds and roughly doubles steering success rates, while leaving the mean of automated interpretability scores essentially unchanged. Finally, in the regularized setting, activation steering success becomes better predicted by auto-interpretability scores, suggesting that regularization can align text-based feature explanations with functional controllability.

Piotr Jedryszek, Oliver M. Crook

Department of Biology, University of Oxford, Oxford, UK · Kavli Institute for Nanoscience Discovery, University of Oxford, Oxford, UK · Department of Chemistry, University of Oxford, Oxford, UK

Sparse AutoencodersLLM InterpretabilityWeight DecayActivation Steering
AskPDF
Mar 3, 2026

Conditioned Activation Transport for T2I Safety Steering

Despite their impressive capabilities, current Text-to-Image (T2I) models remain prone to generating unsafe and toxic content. While activation steering offers a promising inference-time intervention, we observe that linear activation steering frequently degrades image quality when applied to benign prompts. To address this trade-off, we first construct SafeSteerDataset, a contrastive dataset containing 2300 safe and unsafe prompt pairs with high cosine similarity. Leveraging this data, we propose Conditioned Activation Transport (CAT), a framework that employs a geometry-based conditioning mechanism and nonlinear transport maps. By conditioning transport maps to activate only within unsafe activation regions, we minimize interference with benign queries. We validate our approach on two state-of-the-art architectures: Z-Image and Infinity. Experiments demonstrate that CAT generalizes effectively across these backbones, significantly reducing Attack Success Rate while maintaining image fidelity compared to unsteered generations. Warning: This paper contains potentially offensive text and images.

Maciej Chrabąszcz, Aleksander Szymczyk, Jan Dubiński +3

NASK National Research Institute, Warsaw, Poland · Warsaw University of Technology, Warsaw, Poland · Tooplox +2

Safe T2I GenerationActivation SteeringT2I Diffusion Models
AskPDF
Mar 2, 2026

DreamReader: An Interpretability Toolkit for Text-to-Image Models

Despite the rapid adoption of text-to-image (T2I) diffusion models, causal and representation-level analysis remains fragmented and largely limited to isolated probing techniques. To address this gap, we introduce DreamReader: a unified framework that formalizes diffusion interpretability as composable representation operators spanning activation extraction, causal patching, structured ablations, and activation steering across modules and timesteps. DreamReader provides a model-agnostic abstraction layer enabling systematic analysis and intervention across diffusion architectures. Beyond consolidating existing methods, DreamReader introduces three novel intervention primitives for diffusion models: (1) representation fine-tuning (LoReFT) for subspace-constrained internal adaptation; (2) classifier-guided gradient steering using MLP probes trained on activations; and (3) component-level cross-model mapping for systematic study of transferability of representations across modalities. These mechanisms allows us to do lightweight white-box interventions on T2I models by drawing inspiration from interpretability techniques on LLMs. We demonstrate DreamReader through controlled experiments that (i) perform activation stitching between two models, and (ii) apply LoReFT to steer multiple activation units, reliably injecting a target concept into the generated images. Experiments are specified declaratively and executed in controlled batched pipelines to enable reproducible large-scale analysis. Across multiple case studies, we show that techniques adapted from language model interpretability yield promising and controllable interventions in diffusion models. DreamReader is released as an open source toolkit for advancing research on T2I interpretability.

Nirmalendu Prakash, Narmeen Oozeer, Michael Lan +6

Singapore University of Technology and Design · Martian · Thoughtworks +2

Diffusion ModelsT2I Diffusion ModelsActivation SteeringActivation Patching
AskPDF
Feb 28, 2026

Weight Updates as Activation Shifts: A Principled Framework for Steering

Activation steering promises to be an extremely parameter-efficient form of adaptation, but its effectiveness depends on critical design choices -- such as intervention location and parameterization -- that currently rely on empirical heuristics rather than a principled foundation. We establish a first-order equivalence between activation-space interventions and weight-space updates, deriving the conditions under which activation steering can replicate fine-tuning behavior. This equivalence yields a principled framework for steering design and identifies the post-block output as a theoretically-backed and highly expressive intervention site. We further explain why certain intervention locations outperform others and show that weight updates and activation updates play distinct, complementary functional roles. This analysis motivates a new approach -- joint adaptation -- that trains in both spaces simultaneously. Our post-block steering achieves accuracy within 0.2%-0.9%$ of full-parameter tuning, on average across tasks and models, while training only 0.04% of model parameters. It consistently outperforms prior activation steering methods such as ReFT and PEFT approaches including LoRA, while using significantly fewer parameters. Finally, we show that joint adaptation often surpasses the performance ceilings of weight and activation updates in isolation, introducing a new paradigm for efficient model adaptation.

Dyah Adila, John Cooper, Alexander Yun +2

Department of Computer Science, University of Wisconsin-Madison

Activation SteeringParameter-Efficient Fine-Tuning
AskPDF
Feb 27, 2026

Steering and Rectifying Latent Representation Manifolds in Frozen Multi-modal LLMs for Video Anomaly Detection

Video anomaly detection (VAD) aims to identify abnormal events in videos. Traditional VAD methods generally suffer from the high costs of labeled data and full training, thus some recent works have explored leveraging frozen multi-modal large language models (MLLMs) in a tuning-free manner to perform VAD. However, their performance is limited as they directly inherit pre-training biases and cannot adapt internal representations to specific video contexts, leading to difficulties in handling subtle or ambiguous anomalies. To address these limitations, we propose a novel intervention framework, termed SteerVAD, which advances MLLM-based VAD by shifting from passively reading to actively steering and rectifying internal representations. Our approach first leverages the gradient-free representational separability analysis (RSA) to identify top attention heads as latent anomaly experts (LAEs) which are most discriminative for VAD. Then a hierarchical meta-controller (HMC) generates dynamic rectification signals by jointly conditioning on global context and these LAE outputs. The signals execute targeted, anisotropic scaling directly upon the LAE representation manifolds, amplifying anomaly-relevant dimensions while suppressing inherent biases. Extensive experiments on mainstream benchmarks demonstrate our method achieves state-of-the-art performance among tuning-free approaches requiring only 1% of training data, establishing it as a powerful new direction for video anomaly detection. The code will be released upon the publication.

Zhaolin Cai, Fan Li, Huiyu Duan +2

Xinjiang University · Xi’an Jiao Tong University · Shanghai Jiao Tong University +1

Video Anomaly DetectionMultimodal Anomaly DetectionActivation SteeringVLM AdaptationMultimodal Large Language Models
AskPDF
Feb 27, 2026

Suppressing Prior-Comparison Hallucinations in Radiology Report Generation via Semantically Decoupled Latent Steering

Automated radiology report generation using vision-language models (VLMs) is limited by the risk of prior-comparison hallucination, where the model generates historical findings unsupported by the current study. We address this challenge with a training-free, inference-time control framework termed Semantically Decoupled Latent Steering (SDLS). Unlike generic activation steering, which often suffers from semantic entanglement, our approach constructs a semantic-free intervention vector via large language model (LLM)-driven semantic decomposition followed by QRQR-based orthogonalization. This orthogonalization step is critical. It leverages geometric constraints to filter out the clinical semantics often entangled in standard principal component analysis (PCA) directions, ensuring that the steering vector targets only the ``historical comparison" axis. We validate our method on the BiomedGPT foundation model, demonstrating that it overcomes the trade-off between hallucination suppression and clinical accuracy. Extensive experiments on MIMIC-CXR, and zero-shot transfer evaluation on CheXpert Plus and IU-Xray, demonstrate the robustness of our approach. Quantitative evaluations on MIMIC-CXR show that our approach significantly reduces the probability of historical hallucinations (FilBERT score decreases from 0.2373 to 0.1889) and improves clinical label fidelity (CheXpert macro-F1 increases from 0.2242 to 0.3208). Supplementary evaluations confirm that the structural integrity of the clinical narrative is maintained.

Ao Li, Rui Liu, Mingjie Li +6

University of New South Wales · Australian Artificial Intelligence Institute, University of Technology Sydney · Stanford University +3

Radiology Report GenerationVLM Hallucination MitigationRadiology VLMsActivation Steering
AskPDF
Feb 26, 2026

Interpreting and Steering State-Space Models via Activation Subspace Bottlenecks

State-space models (SSMs) have emerged as an efficient strategy for building powerful language models, avoiding the quadratic complexity of computing attention in transformers. Despite their promise, the interpretability and steerability of modern SSMs remain relatively underexplored. We take a major step in this direction by identifying activation subspace bottlenecks in the Mamba family of SSM models using tools from mechanistic interpretability. We then introduce a test-time steering intervention that simply multiplies the activations of the identified bottlenecks by a scalar. Across 7 SSMs and 6 diverse benchmarks, this intervention improves performance by an average of 8.27%, without requiring any task-specific tuning. Finally, we validate that the identified bottlenecks are indeed hindering performance by modifying them to yield an architecture we call Stable-Mamba, which achieves long-context performance gains when retrained from scratch.

Vamshi Sunku Mohan, Kaustubh Gupta, Aneesha Das +1

AppViewX, Bangalore · Independent Researcher · Microsoft Research, Redmond

State Space Language ModelsState Space ModelsLanguage Model SteeringLLM InterpretabilitySelective SSMsActivation Steering
AskPDF
Feb 22, 2026

Facet-Level Persona Control by Trait-Activated Routing with Contrastive SAE for Role-Playing LLMs

Personality control in Role-Playing Agents (RPAs) is commonly achieved via training-free methods that inject persona descriptions and memory through prompts or retrieval-augmented generation, or via supervised fine-tuning (SFT) on persona-specific corpora. While SFT can be effective, it requires persona-labeled data and retraining for new roles, limiting flexibility. In contrast, prompt- and RAG-based signals are easy to apply but can be diluted in long dialogues, leading to drifting and sometimes inconsistent persona behavior. To address this, we propose a contrastive Sparse AutoEncoder (SAE) framework that learns facet-level personality control vectors aligned with the Big Five 30-facet model. A new 15,000-sample leakage-controlled corpus is constructed to provide balanced supervision for each facet. The learned vectors are integrated into the model's residual space and dynamically selected by a trait-activated routing module, enabling precise and interpretable personality steering. Experiments on Large Language Models (LLMs) show that the proposed method maintains stable character fidelity and output quality across contextualized settings, outperforming Contrastive Activation Addition (CAA) and prompt-only baselines. The combined SAE+Prompt configuration achieves the best overall performance, confirming that contrastively trained latent vectors can enhance persona control while preserving dialogue coherence. Dataset is available at: https://github.com/lunat5078/BigFive-Personality-Facets-Dataset

Wenqiu Tang, Zhen Wan, Takahiro Komamizu +1

Nagoya University, Nagoya, Aichi, Japan · Kyoto University, Kyoto, Japan

Persona-Conditioned GenerationLarge Language Model-Based Role-Play SimulationPersonality Modeling in Language ModelsActivation Steering
AskPDF
Feb 22, 2026

Post-Routing Arithmetic in Llama-3: Last-Token Result Writing and Rotation-Structured Digit Directions

We study three-digit addition in Meta-Llama-3-8B (base) under a one-token readout to characterize how arithmetic answers are finalized after cross-token routing becomes causally irrelevant. Causal residual patching and cumulative attention ablations localize a sharp boundary near layer~17: beyond it, the decoded sum is controlled almost entirely by the last input token and late-layer self-attention is largely dispensable. In this post-routing regime, digit(-sum) direction dictionaries vary with a next-higher-digit context but are well-related by an approximately orthogonal map inside a shared low-rank subspace (low-rank Procrustes alignment). Causal digit editing matches this geometry: naive cross-context transfer fails, while rotating directions through the learned map restores strict counterfactual edits; negative controls do not recover.

Yao Yan

Chongqing Normal University Chongqing Key Lab of Cognitive Intelligence and Intelligent Finance Chongqing, China

Numerical Reasoning in Language ModelsCircuits in Language ModelsCausal Interventions in Language ModelsActivation SteeringRepresentation Alignment
AskPDF
Feb 19, 2026

Understanding Unreliability of Steering Vectors in Language Models: Geometric Predictors and the Limits of Linear Approximations

Steering vectors are a lightweight method for controlling language model behavior by adding a learned bias to the activations at inference time. Although effective on average, steering effect sizes vary across samples and are unreliable for many target behaviors. In my thesis, I investigate why steering reliability differs across behaviors and how it is impacted by steering vector training data. First, I find that higher cosine similarity between training activation differences predicts more reliable steering. Second, I observe that behavior datasets where positive and negative activations are better separated along the steering direction are more reliably steerable. Finally, steering vectors trained on different prompt variations are directionally distinct, yet perform similarly well and exhibit correlated efficacy across datasets. My findings suggest that steering vectors are unreliable when the latent target behavior representation is not effectively approximated by the linear steering direction. Taken together, these insights offer a practical diagnostic for steering unreliability and motivate the development of more robust steering methods that explicitly account for non-linear latent behavior representations.

Joschka Braun

Eberhard Karls University of Tübingen Faculty of Science

Language Model SteeringActivation SteeringLLM ReliabilityRepresentation Geometry in Language Models
AskPDF
Feb 19, 2026

ODESteer: A Unified ODE-Based Steering Framework for LLM Alignment

Activation steering, or representation engineering, offers a lightweight approach to align large language models (LLMs) by manipulating their internal activations at inference time. However, current methods suffer from two key limitations: (i) the lack of a unified theoretical framework for guiding the design of steering directions, and (ii) an over-reliance on one-step steering that fail to capture complex patterns of activation distributions. In this work, we propose a unified ordinary differential equations (ODEs)-based theoretical framework for activation steering in LLM alignment. We show that conventional activation addition can be interpreted as a first-order approximation to the solution of an ODE. Based on this ODE perspective, identifying a steering direction becomes equivalent to designing a barrier function from control theory. Derived from this framework, we introduce ODESteer, a kind of ODE-based steering guided by barrier functions, which shows empirical advancement in LLM alignment. ODESteer identifies steering directions by defining the barrier function as the log-density ratio between positive and negative activations, and employs it to construct an ODE for multi-step and adaptive steering. Compared to state-of-the-art activation steering methods, ODESteer achieves consistent empirical improvements on diverse LLM alignment benchmarks, a notable 5.7%5.7\% improvement over TruthfulQA, 2.5%2.5\% over UltraFeedback, and 2.4%2.4\% over RealToxicityPrompts. Our work establishes a principled new view of activation steering in LLM alignment by unifying its theoretical foundations via ODEs, and validating it empirically through the proposed ODESteer method.

Hongjue Zhao, Haosen Sun, Jiangtao Kong +8

University of Illinois Urbana-Champaign · Northwestern University · William & Mary +2

Language Model SteeringActivation SteeringLLM AlignmentInference-Time Language Model Alignment
AskPDF
Feb 19, 2026

Discovering Universal Activation Directions for PII Leakage in Language Models

Modern language models exhibit rich internal structure, yet little is known about how privacy-sensitive behaviors, such as personally identifiable information (PII) leakage, are represented and modulated within their hidden states. We present UniLeak, a mechanistic-interpretability framework that identifies universal activation directions: latent directions in a model's residual stream whose linear addition at inference time consistently increases the likelihood of generating PII across prompts. These model-specific directions generalize across contexts and amplify PII generation probability, with minimal impact on generation quality. UniLeak recovers such directions without access to training data or groundtruth PII, relying only on self-generated text. Across multiple models and datasets, steering along these universal directions substantially increases PII leakage compared to existing prompt-based extraction methods. Our results offer a new perspective on PII leakage: the superposition of a latent signal in the model's representations, enabling both risk amplification and mitigation.

Leo Marchyok, Zachary Coalson, Sungho Keum +2

Oregon State University, Corvallis OR, USA · Korea Advanced Institute of Science & Technology, Daejeon, South Korea.

Privacy Leakage in Language ModelsLLM InterpretabilityMechanistic InterpretabilityActivation Steering
AskPDF
Feb 17, 2026

PERSONA: Dynamic and Compositional Inference-Time Personality Control via Activation Vector Algebra

Current methods for personality control in Large Language Models rely on static prompting or expensive fine-tuning, failing to capture the dynamic and compositional nature of human traits. We introduce PERSONA, a training-free framework that achieves fine-tuning level performance through direct manipulation of personality vectors in activation space. Our key insight is that personality traits appear as extractable, approximately orthogonal directions in the model's representation space that support algebraic operations. The framework operates through three stages: Persona-Base extracts orthogonal trait vectors via contrastive activation analysis; Persona-Algebra enables precise control through vector arithmetic (scalar multiplication for intensity, addition for composition, subtraction for suppression); and Persona-Flow achieves context-aware adaptation by dynamically composing these vectors during inference. On PersonalityBench, our approach achieves a mean score of 9.60, nearly matching the supervised fine-tuning upper bound of 9.61 without any gradient updates. On our proposed Persona-Evolve benchmark for dynamic personality adaptation, we achieve up to 91% win rates across diverse model families. These results provide evidence that aspects of LLM personality are mathematically tractable, opening new directions for interpretable and efficient behavioral control.

Xiachong Feng, Liang Zhao, Weihong Zhong +5

Harbin Institute of Technology · The University of Hong Kong

Controllable Text GenerationPersonality Modeling in Language ModelsActivation SteeringRepresentation Geometry in Language Models
AskPDF
Feb 15, 2026

Watch the Model Think: On-Policy Extraction of Activation Steering Vectors

When a model solves a problem on one attempt and fails it on the next, what separates the two is rarely the final answer token; it is the trajectory that reached it. Contrastive activation steering leaves that signal unused: CAA, SADI, RepE and ITI build their direction from experimenter-supplied text, recorded while the model reads rather than reasons. That choice also caps what the vector can express, since polarity must be written into the text, and a task judged only by outcome offers nothing to write it with. ROAST makes the trajectory itself the contrast: sample rollouts, let an outcome verifier split them into successes and failures, and contrast the reasoning that worked against the reasoning that did not. A matched teacher-forced control---rollouts, labels, answer text and pair counts held fixed, the trajectory alone stripped---points to the trajectory as what matters: on GSM8K at 0.6B the pairs alone buy +0.12 points while restoring the trajectories buys +6.05, the larger and only seed-robust step. Replacing the trajectory with an equal-length neutral prefix or another question's reasoning falls below no intervention. The two corpora are also far apart geometrically, a median 70+ degrees apart at both Qwen3 scales probed, beyond what a split-half null explains. Reading from rollouts calls for two corrections---keeping the full difference vector rather than Top-10% masking, and giving each question one vote rather than one per pair---and only grouped aggregation beats the unsteered baseline under 20% verifier noise. On parser-free benchmarks (GSM8K, MATH500, IFEval), ROAST is best in all six cells over two models, by up to +9.7, at +6.4% wall-clock and no added context; it also leads on six parser-scored benchmarks across three models. Across nine models (0.6B--122B, four families), ROAST improves on the unsteered model at every scale. Code: https://github.com/TomySu404/ORBIT

Xuanbo Su, Yingfang Zhang, Hao Luo +3

Bairong Inc., Beijing, China · School of Mathematics, Harbin Institute of Technology, Harbin, China

Language Model SteeringRepresentation SteeringActivation SteeringReasoning Trace Analysis
AskPDF
Feb 12, 2026

Sparse Autoencoders are Capable LLM Jailbreak Mitigators

Jailbreak attacks remain a persistent threat to large language model safety. We propose Context-Conditioned Delta Steering (CC-Delta), an SAE-based defense that identifies jailbreak-relevant sparse features by comparing token-level representations of the same harmful request with and without jailbreak context. Using paired harmful/jailbreak prompts, CC-Delta selects features via statistical testing and applies inference-time mean-shift steering in SAE latent space. Across four aligned instruction-tuned models and twelve jailbreak attacks, CC-Delta achieves comparable or better safety-utility tradeoffs than baseline defenses operating in dense latent space. In particular, our method clearly outperforms dense mean-shift steering on all four models, and particularly against out-of-distribution attacks, showing that steering in sparse SAE feature space offers advantages over steering in dense activation space for jailbreak mitigation. Our results suggest off-the-shelf SAEs trained for interpretability can be repurposed as practical jailbreak defenses without task-specific training.

Yannick Assogba, Jacopo Cortellazzi, Javier Abad +3

1Apple · 2ETH Zurich

Sparse AutoencodersLLM Jailbreak AttacksJailbreak DefenseActivation Steering
AskPDF
Feb 12, 2026

TADA! Tuning Audio Diffusion Models through Activation Steering

Audio diffusion models can synthesize high-fidelity music from text, yet achieving fine-grained control over specific musical attributes remains challenging, as their internal mechanisms for representing high-level concepts are poorly understood. In this work, we use activation patching to demonstrate that recent audio diffusion architectures exhibit a semantic bottleneck, where a small, shared subset of consecutive attention layers controls distinct musical concepts, such as the presence of specific instruments, vocals, or genres. Building on this, we systematically evaluate a broad spectrum of steering paradigms, comparing activation steering against prompt-level, score-space, and weight-space interventions, analyzing the interaction between the steering mechanism and the intervention site. Our new benchmark, supported by an extensive user study, demonstrates that localized activation steering establishes a new state-of-the-art in audio concept modulation.

Łukasz Staniszewski, Katarzyna Zaleska, Mateusz Modrzejewski +1

Warsaw University of Technology · IDEAS Research Institute

Controllable Music GenerationAudio Diffusion ModelsActivation Steering
AskPDF
Feb 11, 2026

General and Efficient Steering of Diffusion Models

Steering diffusion models toward conditions unseen during training typically requires either retraining with conditional inputs or per-step gradient computations, both of which incur substantial computational overhead. We present Noise-Aligned RFM Steering (NA-RFM), a general recipe for efficiently steering diffusion models without gradient guidance during inference, enabling fast controllable generation. The method combines two offline-computed signals: noise alignment, a high-noise correction from PCA statistics of the target examples and the full data, and Recursive Feature Machine (RFM) activation steering, which learns a target-discriminative direction from labeled forward-process activations. During sampling, noise alignment provides coarse control at high noise, while the RFM direction is reused over intermediate/late timesteps through lightweight activation edits. Experiments on CIFAR-10, ImageNet, CelebA, and fine-grained bird species show improved target accuracy over gradient-based post-hoc guidance baselines, improved FID on the class-guidance benchmarks, and substantial inference speedups. Code: https://github.com/isotrivial/na-rfm.

Qingsong Wang, Mikhail Belkin, Yusu Wang

Halıcıoğlu Data Science Institute, University of California San Diego, La Jolla, CA, USA

Diffusion Model GuidanceActivation SteeringControllable Image GenerationDiffusion Model Inference AccelerationDiffusion-Based Denoising
AskPDF
Feb 9, 2026

Mitigating Memorization Where It Happens

Large language models (LLMs) can memorize and reproduce training sequences verbatim, raising privacy and copyright concerns. Existing mitigation methods apply interventions uniformly, often degrading performance on the majority of tokens that generalize normally. We study a token-level log-likelihood ratio between a target model and a domain-competent reference with lower exposure to the evaluated sequences. Exposure-controlled experiments support its use for localizing positions associated with sequence-level verbatim recall. Across evaluated settings, a minority of positions carries a disproportionate share of the positive signal, motivating selective activation correction. From the ideal memorization reduction objective, we derive a probe--steer framework which decomposes intervention into a probe that detects memorization-relevant activations and a steer that applies targeted correction only when the probe exceeds a threshold. We propose Gated Subspace Steering (GSS) as its practical instantiation: the optimal probe--steer pair admits a closed-form solution as the leading singular vectors of a gradient-weighted activation matrix. Across four benchmarks, GSS matches or exceeds state-of-the-art memorization reduction while requiring 10--100×\times less compute than optimization-based alternatives.

Xuanqi Zhang, Haoyang Shang, Xiaoxiao Li

University of British Columbia · Vector Institute · Independent Researcher

Memorization in Language ModelsPrivacy Leakage in Language ModelsActivation Steering
AskPDF