Llama 3
Meta
rich detail 11 method fields published
Evaluation
Llama Guard 3 system-level safety evaluation
System-level safety with Llama Guard 3 trained on 13 AI Safety taxonomy hazard categories (Child Sexual Exploitation, Defamation, Elections, Hate, Indiscriminate Weapons, Intellectual Property, Non-Violent Crimes, Privacy, Sex-Related Crimes, Sexual Content, Specialized Advice, Suicide & Self-Harm, Violent Crimes) plus Code Interpreter Abuse; measures violation reduction across capabilities and per harm category (Tables 25-26)
How it was run
Open a release to see the setup, scoring, and other details that the lab published. Only fields the lab actually disclosed are shown.