arxiv
PublishedSeptember 1, 2026 at 4:00 AM
—neutral
Triggering Chain-of-Thought via Latent Feature Interventions in Large Language Models
Publisher summary· verbatim
arXiv:2601.08058v2 Announce Type: replace-cross Abstract: Chain-of-Thought (CoT) prompting often improves the reasoning performance of large language models (LLMs), but the internal signal that triggers this behavior remains poorly understood. Leveraging the sparse features captured by Sparse Autoen
Stay posted· Newsletter
A 5-min weekly brief — top movers, price watch, story of the week.
Discussion
No replies yet. Be first.
Related coverage
More from ARXIV
arxivCulturalMenuBench: Probing the Knowledge-Application Gap in Multimodal Culinary Reasoning8harxivProactive Service Agents: A Unified Decision Framework, Methods, and Evaluation8harxivX-Translator: A Real-Time Multilingual Speaker-Aware Speech-to-Speech Translation System8harxivA Blind Trust, the Bloody Thrust: When Attacker-Controlled Hook Updates Steer AI Agent Harnesses towards Malicious Behaviors8hThe Bubble Brief
WEEKLYRead AI insights every Tuesday — top movers, new releases, story of the week.
Originally published on arxiv ↗