arXiv:2509. 25045v3 Announce Type: replace-cross Abstract: Despite their capabilities, Large Language Models (LLMs) remain opaque with limited understanding of their internal representations.
Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.
arXiv:2606. 26620v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) have emerged as a powerful tool for decomposing superposed language model representations into sparse and interpretable features.
arXiv:2512. 10092v2 Announce Type: replace Abstract: Analyzing large-scale text corpora is a core challenge in machine learning, crucial for tasks like identifying undesirable model behaviors or biases in training data.
arXiv:2506. 20040v3 Announce Type: replace-cross Abstract: Interpreting language models remains challenging due to the existence of residual stream, which linearly mixes and duplicates features across adjacent layers, causing single-layer analyses to miss this cross-layer structure.
arXiv:2607. 04222v1 Announce Type: new Abstract: Interpretability methods aim to reveal the features represented inside large language models (LLMs).
arXiv:2606. 11722v1 Announce Type: cross Abstract: Finding interpretable directions in language-model representations is critical for understanding and controlling model behavior.
arXiv:2601. 22588v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are widely used as reference-free evaluators via prompting, but this "LLM-as-a-Judge" paradigm is costly, opaque, and sensitive to prompt design.