arXiv:2608. 02632v1 Announce Type: new Abstract: Circuit tracing is an exciting technique for revealing the internal computation of language models, but it requires a time-intensive manual step of grouping individual features or MLP neurons into supernodes.
Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.
arXiv:2603. 21014v2 Announce Type: replace Abstract: Mechanistic interpretability seeks to understand how Large Language Models (LLMs) represent and process information.
arXiv:2606. 28548v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) have become a useful tool for extracting interpretable features in language models.
arXiv:2512. 14332v2 Announce Type: replace-cross Abstract: The field of Language Reasoning Models (LRMs) has been very active over the past few years with advances in training and inference techniques enabling LRMs to reason longer, and more accurately.
arXiv:2607. 22610v1 Announce Type: new Abstract: When a language model produces a response in a multi-turn conversation, which tokens from prior turns shaped that answer, and how did those dependencies propagate across prior turns?
arXiv:2601. 22594v2 Announce Type: replace-cross Abstract: The high-level concepts that a neural network uses to perform computation need not be aligned to individual neurons (Smolensky, 1986).
As artificial intelligence and machine learning (AI/ML) models become integral to network operations, their lack of transparency poses a significant barrier to operator trust. Existing explainable artificial intelligence (XAI) techniques often fail to bridge this gap for non-specialists, producing technical outputs that are difficult to translate into actionable insights.