#Safeguards
Showing 2 of 2 repositories tagged #safeguards, ranked by stars
wisent-ai
wisent
This is an open-source version of the representation engineering framework for stopping harmful outputs or hallucinations on the level of activations. 100% free, self-hosted and open-source.
Score
0
★ 343
⑂ 33
—
Python
rishub-tamirisa
tamper-resistance
[ICLR 2025] Official Repository for "Tamper-Resistant Safeguards for Open-Weight LLMs"
Score
0
★ 68
⑂ 8
—
Python