axbench
Stanford NLP Python library for benchmarking the utility of LLM interpretability methods
stanfordnlp/axbench
View on GitHub ↗Stanford NLP Python library for benchmarking the utility of LLM interpretability methods
axbench grew +0.5% in the last 30 days, ranks 43rd of 71 in Interpretability & Alignment, last commit 226 days ago.
Star trajectory
115 days tracked2026-07-02218 stars today2026-10-25
Momentum
+0.5% in 30d, above the Interpretability & Alignment median of +0.2%.
Maintenance
Last commit 226 days ago, staler than the median of 202d.
How it compares in Interpretability & Alignment
axbench
218
stars
+0.5% 30d
commit 226 days ago
Interpretability & Alignment median
298
stars
+0.2% 30d
commit ~202d ago
Leader · lmms-eval
4.5k
stars
+0.8% 30d
commit 2 days ago
Ranked 43rd of 71 by stars.
- Language
- Python
- License
- Apache License 2.0
- Contributors
- 9
- Forks
- 44
- Watchers
- 3
- Open issues
- 12
- Releases
- 0
- Created
- 2024-08-07
- Stars this week
- +0
You've seen where axbench stands today.
Get the moves before everyone else: the 5 Interpretability & Alignment repos climbing fastest, every Tuesday.
Free weekly digest. Double opt-in, unsubscribe anytime.