Matryoshka Attribution (MAttr) is a mask‑learning method that identifies nested subsets of a language model’s internal components by minimizing downstream loss. It uses a differentiable sigmoid top‑k operator and randomizes sparsity during training to produce an attribution ordering of components. MAttr tops the Mechanistic Interpretability Benchmark leaderboard and can be applied via reinforcement learning to pinpoint weight changes that control behaviors such as refusal in Llama 3.1 8B Instruct, where restoring just 1% of weights removes refusals while preserving capabilities.
arXiv:2605. 23393v2 Announce Type: replace-cross Abstract: Mechanistic interpretability of transformers requires identifying not just which components matter but how they compose into the computational route that produced a prediction.
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:2608. 08829v1 Announce Type: cross Abstract: Activation steering edits the behaviour of a frozen language model by adding a learned vector to its residual stream, and current practice fixes the injection layers globally per task.
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:2606. 05165v1 Announce Type: new Abstract: Training Data Attribution (TDA) seeks to trace a model's predictions back to its training data.
arXiv:2606. 29171v1 Announce Type: cross Abstract: While existing data attribution methods can identify which training examples build specific mechanistic circuits, they cannot explain how training data shapes the high-level behavioral decisions a model learns to make.
arXiv:2602. 02470v2 Announce Type: replace Abstract: Autoregressive large language models (LLMs) have achieved remarkable success in many complex tasks, yet they can still fail in very simple logical reasoning such as the "reversal curse" -- when trained on forward knowledge data of the form "$A \rightarrow B$" (e.
Large language models increasingly operate as tool-using agents, where small format, argument, or function-call errors can invalidate otherwise plausible responses. We study inference-time feed-forward network (FFN) intervention for improving structured outputs without retraining model weights.
arXiv:2609.15064v1 Announce Type: new Abstract: Reinforcement learning (RL) is widely utilized in large language model training to improve targeted capabilities, yet how RL reshapes a model remains p...
arXiv:2609. 26290v1 Announce Type: cross Abstract: Causal tabular foundation models amortize effect estimation across synthetic mechanisms, but latent-effect supervision rewards posterior shrinkage instead of directly encoding the repeated-sample response needed in a fixed deployment population.
arXiv:2605.14040v2 Announce Type: replace Abstract: Trackable improvement in multimodal physics reasoning rests on a training-and-evaluation system that is itself rarely verified: the corpora a model...
The paper proposes that two architectural assumptions—(1) attention and MLPs share a key‑value form <phi(S)>U, and (2) components read from an additive residual stream—are sufficient to answer three interpretability questions: component interaction, information routing, and token attribution. By treating these selections as a computational graph, the authors develop Unpack, a backward attribution method that validates interaction scores, recovered routes, and token attribution against established tests across models ranging from 160M to 6.9B parameters. The study also shows that contribution and causal effect can differ, with a recognizable signature in how components change when a task is removed.