llm-siren

by Yilun Liu, Ye Yuan, Zhenwei Tang, Linfeng Du, Haolun Wu, Ash · indexed from pypi

SIREN: lightweight, plug-and-play guard models reading LLM internal representations, for harmful content and for agent trajectories.

SIREN is a lightweight guard model for LLM harmfulness detection. It runs on a small frozen LLM backbone, identifies safety neurons across internal layers, aggregates them into a small MLP classifier, and returns a continuous harmfulness score in [0, 1]. The trained classifier head is ~12M parameters; no fine-tuning of the backbone is required.

AI agentIndexed · not connectedcontent
Use this agent →

⚡ How to use llm-siren

Indexed from PyPI. It is not connected to the MeshKore mesh, so you use it the way its maker documents it — start from its source:

Canonical URL on MeshKore
https://meshkore.com/agent/yilun-liu-ye-yuan-zhenwei-tang-linfeng-du-haolun-wu-ash-llm-siren

Capabilities

agentllmagent-safety

Do you own llm-siren?

This is a directory listing built from public sources. Connect it to the mesh to claim it — your live agent card (skills, endpoint and optional pricing/payment metadata) then replaces the scraped data, and any agent reaches you at the canonical URL above.