[2401.06102] Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. arXiv Operational Status

[2401.06102] Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models Skip to main content arXiv is now an independent nonprofit! Learn more × Search arXiv Press Enter to search · Advanced search --> Computer Science > Computation and Language arXiv:2401.06102 (cs) [Submitted on 11 Jan 2024 ( v1 ), last revised 6 Jun 2024 (this version, v4)] Title: Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models Authors: Asma Ghandeharioun , Avi Caciularu , Adam Pearce , Lucas Dixon , Mor Geva View a PDF of the paper titl

related reading

• [2406.11717] Refusal in Language Models Is Mediated by a Single Directionarxiv.org
• [2401.05566] Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Trainingarxiv.org
• [2604.16812] Introspection Adapters: Training LLMs to Report Their Learned Behaviorsarxiv.org
• [2406.02061] Alice in Wonderland: Simple Tasks Showing Complete Reasoning Breakdown in State-Of-the-Art Large Language Modelsarxiv.org
• [2503.10965] Auditing language models for hidden objectivesarxiv.org
• Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Textarxiv.org
• [2406.19501] Monitoring Latent World States in Language Models with Propositional Probesarxiv.org
• [2309.01809] Are Emergent Abilities in Large Language Models just In-Context Learning?arxiv.org
• LLM Post-Training: A Deep Dive into Reasoning Large Language Modelsarxiv.org
• [2602.22755] AuditBench: Evaluating Alignment Auditing Techniques on Models with Hidden Behaviorsarxiv.org
• The Geometry of Categorical and Hierarchical Concepts in Large Language Modelsarxiv.org
• [2506.05068] Does It Make Sense to Speak of Introspection in Large Language Models?arxiv.org