arXiv:2606. 16920v1 Announce Type: cross Abstract: Circuit discovery is a key technique in mechanistic interpretability to pinpoint the model components that are crucial for performing a given task.
arXiv:2601. 09624v2 Announce Type: replace-cross Abstract: Machine unlearning is becoming essential for building trustworthy and compliant language models.
The paper investigates mechanistic interpretability, focusing on how automated circuit discovery is evaluated. It shows that the commonly used faithfulness objective can favor circuits that reproduce a model’s behavior poorly, creating an objective-level recovery gap. Experiments on four human-reference tasks and InterpBench reveal that many discovery methods misrank candidate circuits, and that restoring excluded signals can correct most of these misrankings without altering the circuits’ behavior.
The paper investigates whether structural differences in circuits discovered by circuit discovery methods reflect distinct mechanisms. By varying input-token frequency while keeping the task constant, the authors find that although circuits appear specialized by frequency structurally, functional and representational analyses reveal no reliable differences, a phenomenon they call phantom specialization. Across multiple models and tasks, structurally distinct circuits implement the same computation, with core shared subgraphs recovering most of the performance and interchangeable internal representations confirmed by causal interventions.
The study investigates the consistency and specificity of language model circuits across six tasks and five models, focusing on component-level (attention heads and MLP blocks) and neuron-level circuits. Component-level circuits are highly consistent and causally important but lack task specificity, as ablating a circuit for one task similarly harms performance on other tasks. Neuron-level circuits show higher task specificity but lower consistency, with overlap mainly between closely related tasks. The analysis of Llama‑3.2‑3B reveals that shared components are predominantly MLP blocks, while attention heads act as generic attention‑sink heads.
arXiv:2607. 18921v1 Announce Type: cross Abstract: Circuit extraction identifies a small set of model components whose presence preserves a target behavior under ablation, and the resulting circuit is often read as the mechanism behind that behavior.
The paper introduces Circuit Condensation, a post‑training method that prunes low‑attribution edges from large causal graphs and trains a low‑rank adapter to preserve behavior. Across four behaviors and eight models, the condensed circuits are on average 8.1× smaller than the strongest frozen baseline, with reductions up to 316×. Experiments show that weight updates drive the size reduction, and detailed ablations reveal dependencies among remaining edges and a more focused set of heads for indirect object identification.
arXiv:2609.25602v1 Announce Type: new Abstract: In language models, the choice between believing the prompt and believing the weights is made by a handful of identifiable attention heads. Instruction...
The paper introduces Concept-Targeted Attribution (CTA), a method that trains attribution graphs to explain the emergence of internal concept representations in language models, rather than just the final token prediction. CTA produces probe-specific circuits that reveal which internal computations drive a linear probe’s accuracy, and cross-layer transcoders demonstrate that these graphs contain predictive structure across multiple concept categories. Causal ablations show that probe-targeted and logit-targeted graphs capture distinct mechanisms, with probe-relevant features affecting internal concept scores and logit-relevant features altering generated tokens.
arXiv:2609.35890v1 Announce Type: new Abstract: Sparse-autoencoder decomposability and concentrated feature attribution are increasingly treated as evidence that a model's computation is easier to re...
arXiv:2601. 21996v2 Announce Type: replace-cross Abstract: While Mechanistic Interpretability has identified interpretable circuits in LLMs, their causal origins in training data remain elusive.
arXiv:2608. 05732v1 Announce Type: new Abstract: Controlling the behavior of large language models (LLMs) remains a critical challenge for AI alignment.
arXiv:2605. 28860v2 Announce Type: replace-cross Abstract: Fine-tuning large language models (LLMs) frequently induces catastrophic forgetting of prior capabilities.