Skip to content
#

behavioral-evaluation

Star

Here is 1 public repository matching this topic...

SolomonB14D3 / knowledge-fidelity

Star 0

Behavioral auditing toolkit for LLMs: rho-audit measures factual accuracy, bias, sycophancy, toxicity, and reasoning via teacher-forced confidence probes. SVD compression with knowledge preservation. Steering vectors for runtime behavioral control. 12-model merge audit across SLERP/TIES/DARE-TIES/Linear.

transformers pytorch svd interpretability confidence bias-detection truthfulness model-merging sycophancy llm-compression mergekit activation-engineering model-auditing steering-vectors rho-audit behavioral-evaluation
  • Updated Feb 25, 2026
  • Python

Improve this page

Add a description, image, and links to the behavioral-evaluation topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the behavioral-evaluation topic, visit your repo's landing page and select "manage topics."

Learn more