arXiv (All)
open access
From Trait Vectors to Circuits: Tracing Refusal and Sycophancy Through Language Models
A direction in activation space that changes safety-relevant behavior when steered is not necessarily one the model uses to produce that behavior on its own. We therefore ask whether steering acts through the computation of the unmodified model or through a different set of components, studying two
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
- Safety Reconstructed: Generative Modeling via Masked Diffusion Builds Strong Safety Guardrails#1118707
- Table 2 - d' and logit from Returning to the effects of inhibition of return on lexical decisions#357070
- The Sycophancy Trap: How Misaligned Objective Functions Drive Excessive Accommodation in AI Systems – A Load Minimization Theory Perspective#82723
- Decomposing Refusal Steering in Mixture-of-Experts Models#1048681
- RoPE at the End of Its Rope? Theory, Diagnosis, and Mitigation of Long-Context Failures#1145096
Record · ID 1036907
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