arXiv (All)
open access
Language Model Activations Inhabit Privileged Error-Correcting Basins
Language models exhibit remarkable robustness, continuing to produce coherent text even when their activations are perturbed by interventions like linear steering. We hypothesize that this robustness is a result of passive dynamics, i.e., constraining mechanisms in the forward pass that funnel activ
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
- Learning to Read Out: Unembedding Dynamics in Language Model Pretraining#1356361
- HRIS Validation Study IV — Trajectory Persistence and Basin Re-Entry A Controlled Evaluation of Path Dependence, Transition Cost, and Recovery Dynamics in Language Model Inference#102530
- From a Prompt to Repertoires: Evolving Functional REpertoires Enable LLM Continual Learning#1248653
- Presuppositional TOO, Postsuppositional TOO#702855
- Measuring LLM Sycophancy under Sustained Multi-Turn Pressure#986693
Record · ID 1199457
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