anthropics/
Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".
Archived by Anthropic 32 forks Created Dec 2023 View on GitHub
- Stars
- 157
- <1% of anthropics's stars
- Rank
- #338,667
- of 852,119 repos, top 40%
Among 852,119 repos
100–160 stars: 155,549 repos, including sleeper-agents-paper
top 50%top 10%top 1%top 0.1% 
Stars along the bottom, and repos in each band on a log scale
Quick stats
- Next rank
- +1 star to reach #336,913
- Next milestone
- +64 stars to reach the top 30%
- Popular
- One of 490,778 repos with 100+ stars
- Yearly average
- 54 stars a year since Dec 2023