Skip to content

Llama 3

Named by 2 kept items in this workspace.

The items that name it 2

  • meta-llama/PurpleLlama
    repo2026-07-14

    referenced via Llama 3's Responsible Use Guide recommendation to check/filter LLM inputs and outputs

  • Microsoft Agent Governance Toolkit
    repo2026-05-06It is written here as Llama-3.

    100% attack success rate reported using adaptive attacks with logprob access and suffix optimization (Andriushchenko et al., ICLR 2025), evaluated against JailbreakBench (Chao et al., NeurIPS 2024)

In every workspace you can read 6

Security

All technologies in this workspace.