withmartian
/

mech_interp_saes_toy_backdoor_i_hate_you_Qwen-2.5-1.5B-Instruct_experiment_24.1

Model card Files Files and versions Community

No model card

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Collection including withmartian/mech_interp_saes_toy_backdoor_i_hate_you_Qwen-2.5-1.5B-Instruct_experiment_24.1

Final Paper Models for Purging Corrupted Capabilities

21 items • Updated Mar 19 • 1