arXiv:2607. 01033v1 Announce Type: new Abstract: Model organisms (MOs) - language models trained to exhibit undesired or unnatural behaviours - are frequently used as testbeds for evaluating white-box interpretability techniques.
arXiv:2606. 12360v1 Announce Type: new Abstract: Language-model post-training is the main stage at which model behavior is shaped, yet it still largely involves optimization of scalar rewards that summarize diverse desiderata.
Language-model post-training is the main stage at which model behavior is shaped, yet it still largely involves optimization of scalar rewards that summarize diverse desiderata. This abstraction gives practitioners little visibility into what their data actually teaches models, allowing spurious correlations to be learned by a model and inducing undesirable behaviors such as over-stylization and sycophancy.
arXiv:2606. 02211v1 Announce Type: cross Abstract: Large language models are often influenced by extraneous input features, such as cues revealing a user's preferred answer.
The paper introduces Exemplar Partitioning (EP), an unsupervised technique that constructs interpretable feature dictionaries from large language model activations by clustering streamed activations into Voronoi regions defined by exemplars and their averages. EP allows comparison of dictionaries across layers, checkpoints, and architectures, and demonstrates utility in interpreting model behavior, tracking training dynamics, detecting hidden concepts, and enabling targeted interventions. Experiments on Gemma‑2‑2B and Llama‑3.1‑8B show EP can reveal how instruction tuning reorganizes harmful prompt activations, facilitate interventions that alter model responses, and achieve high concept‑detection performance while requiring far fewer construction tokens than comparable methods.
arXiv:2604.17614v2 Announce Type: replace-cross Abstract: Skills are a natural unit for describing what a language model can do and how its behavior can be changed. However, existing characterization...
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:2603. 01437v2 Announce Type: replace Abstract: As chain of thought (CoT) has become central to scaling reasoning capabilities in large language models (LLMs), it has also emerged as a promising tool for interpretability, suggesting the opportunity to understand model decisions through verbalized reasoning.
arXiv:2607. 00089v1 Announce Type: new Abstract: Mechanistic interpretability has produced a rich inventory of component-level analyses that characterise what neural-network components encode and how they interact.
arXiv:2607. 04222v1 Announce Type: new Abstract: Interpretability methods aim to reveal the features represented inside large language models (LLMs).
arXiv:2606. 32008v1 Announce Type: new Abstract: Mechanistic interpretability (MI) requires full access to model internals, yet the APIs for most widely deployed language models at best expose log-probabilities over output tokens.
arXiv:2607. 16448v1 Announce Type: cross Abstract: Interpretability methods for neural network activations span a wide cost spectrum, from cheap, training-free techniques (such as linear probes, PCA, SVD) to more expensive training-based ones (such as SAEs and activation oracles).
arXiv:2606. 12117v1 Announce Type: cross Abstract: Benchmark scores often misrepresent a large language model's (LLM's) knowledge, because they rely, e.