arXiv (All)
open access
Contrastive Covariance Subspaces for Activation Steering
Activation steering controls large language model behavior by adding a direction to hidden activations during inference. For steering to work well, that direction must be a pure signal for the target concept: any confound entangled with it, such as an incidental topic or writing style, is injected i
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
- Compositional Multilingual and Behavioral Attribute Steering#985765
- Prefilling-dLLM v2: Learned Chunk Routing for Long-Context Diffusion Language Models#1343069
- On the Steering Dimensionality of Refusal in Language Models#1199519
- You Can't Have It Both Ways: Concept Entanglement Limits Diffusion Model Unlearning#1119210
- Preactivation and probabilistic inference coexist during sentence comprehension#361036
Record · ID 1324626
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