arXiv (All)
open access
Decodable In-Context State and Model Output Across Training
Prior work established that a probe can decode an in-context binding on model errors and that probe-guided steering can repair some of them. We follow probe accuracy, model output, and steering response across public pretraining and post-training checkpoints. Probe accuracy rises during Pythia pretr
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
- Refining Ground Truth Poses in Autonomous Driving Datasets via Neural Rendering#1035285
- Distilling Image Prototypes for Guided Test-Time Adaptation#996562
- The Calls are Coming from Inside the Model: Investigating Probe-based Detection of Tool-Calling Errors in LLMs#781045
- The Calls are Coming from Inside the Model: Investigating Probe-based Detection of Tool-Calling Errors in LLMs#779670
- Accountable and uncertainty-aware evaluation of sensor-based AI under distribution shift: devices, subjects, and nearly three years underground#987022
Record · ID 1106100
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