Joe-b-20/CoreVital

Mechanistic interpretability toolkit for monitoring LLM internal health. Features deep tensor-level instrumentation (Self/Cross-Attention, Hidden States) and real-time risk diagnostics.

22
/ 100
Experimental
No Package No Dependents
Maintenance 13 / 25
Adoption 0 / 25
Maturity 9 / 25
Community 0 / 25

How are scores calculated?

Stars

—

Forks

—

Language

Python

License

—

Category

llm-interpretability-explainability

Last pushed

Mar 16, 2026

Commits (30d)

0

GitHub
LLM Interpretability & Explainability · 51 tools

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/Joe-b-20/CoreVital"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

Higher-rated alternatives

filipnaudot/llmSHAP

llmSHAP: a multi-threaded explainability framework using Shapley values for LLM-based outputs.

51

microsoft/automated-brain-explanations

Generating and validating natural-language explanations for the brain.

48

CAS-SIAT-XinHai/CPsyCoun

[ACL 2024] CPsyCoun: A Report-based Multi-turn Dialogue Reconstruction and Evaluation Framework...

44

wesg52/universal-neurons

Universal Neurons in GPT2 Language Models

39

ICTMCG/LLM-for-misinformation-research

Paper list of misinformation research using (multi-modal) large language models, i.e., (M)LLMs.

38

Explore LLM Tools

All categories Trending LLM Tool directory Insights