arXiv (All)
open access
Probing and Steering for Safety-Relevant Behaviours in Large Language Models
Activation probes are computed directions in a language model's residual stream, used both to detect safety-relevant behaviours and, by adding their direction back into the stream, to steer them. We explore how the main design choices behind such probes interact, within one pipeline, on one model (L
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Hard Negatives Reveal What Easy Negatives Hide: Cross-Lingual Harmfulness Representations Degrade with Resource Tier Under Hard Negatives#1064302
- Skin-Deep: A Geometric Diagnostic for Alignment Fragility in Large Language Model Representations#1156399
- SafeEvo: Deciphering the Safety Alignment Mechanism and Evolution in Language Models#1233968
- Are Vision-Language-Action Models Robust to One-Step Observation Perturbations?#1116881
- Language models judge war differently when tested for alignment#971968
Record · ID 1423155
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive