Causal Interventions in Language Models
Overview
This field asks which internal states, features, heads, neurons, or context elements actually influence a language model’s decisions, rather than merely correlate with them. Researchers use counterfactual prompt and evidence edits, activation patching and ablation, causal tracing, sparse-autoencoder features, and inference-time steering or weight edits to test mechanisms and control behavior. Applications include checking whether chain-of-thought and retrieved evidence drive answers, and modifying refusal, hallucination, bias, tool use, or reasoning while preserving unrelated capabilities. Results show that readable representations are often not causally used or easily steered; effects vary by layer, task, model, and context, while redundancy and collateral effects make reliable, selective interventions a continuing challenge.
Latest papers
532 papers55 papers in the last four weeks, down 37% on the four weeks before. 0.4% of all new papers.
Towards Isolated Interventions via Almost Orthogonal Features in Language Models
https://github.com/mrtzmllr/sae-icm.-: Circuit-Restricted Weight Arithmetic for Selective Refusal
Bypassing the Rationale: Causal Auditing of Implicit Reasoning in Language Models
There Is More to Refusal in Large Language Models than a Single Direction
Beyond Dense States: Sparse Transcoders as Causally Testable Operators for LLM Latent Reasoning
Interpreting and Controlling Model Behavior via Constitutions for Atomic Concept Edits
Cross-Lingual Activation Steering for Multilingual Language Models
SteerEval: Inference-time Interventions Strengthen Multilingual Generalization in Neural Summarization Metrics
Tracing the Latent Threads: A Mechanistic Study of How LLMs Represent and Operationalize Race and Ethnicity Cues
To Copy or Not to Copy: Copying Is Easier to Induce Than Recall
reactivation'' process that can be triggered at different locations in the input, while restoring recall is a suppression'' process that is more fragile and strongly tied to object-token interventions.Steering Language Models Before They Speak: Logit-Level Interventions
Triggering Chain-of-Thought via Latent Feature Interventions in Large Language Models
Mechanistic Knobs in LLMs: Retrieving and Steering High-Order Semantic Features via Sparse Autoencoders
SGM: Safety Glasses for Multimodal Large Language Models via Neuron-Level Detoxification
D-STEER: Two-Way Control of DPO-Induced Safety Behavior in Activation Space
LIFT: Likelihood-Based Intervention Faithfulness Training
LLMs Encode Harmfulness and Refusal Separately
When Can Large Reasoning Models Save Thinking? Mechanistic Analysis of Behavioral Divergence in Reasoning
Llama See, Llama Do: A Mechanistic Perspective on Contextual Entrainment and Distraction in LLMs
irrelevant'' contextual information in the input prompt. Specifically, LMs assign significantly higher logits (or probabilities) to any tokens that have previously appeared in the context prompt, even for random tokens. This suggests that contextual entrainment is a mechanistic phenomenon, occurring independently of the relevance or semantic relation of the tokens to the question or the rest of the sentence. We find statistically significant evidence that the magnitude of contextual entrainment is influenced by semantic factors. Counterfactual prompts have a greater effect compared to factual ones, suggesting that while contextual entrainment is a mechanistic phenomenon, it is modulated by semantic factors. We hypothesise that there is a circuit of attention heads -- the entrainment heads -- that corresponds to the contextual entrainment phenomenon. Using a novel entrainment head discovery method based on differentiable masking, we identify these heads across various settings. When we turn off'' these heads, i.e., set their outputs to zero, the effect of contextual entrainment is significantly attenuated, causing the model to generate output that capitulates to what it would produce if no distracting context were provided. Our discovery of contextual entrainment, along with our investigation into LM distraction via the entrainment heads, marks a key step towards the mechanistic analysis and mitigation of the distraction problem.