News for hackers. Stuff that matters.
Re:Show HN: Llama 3.2 Interpretability with Sparse Autoencoders by bubaumba on Saturday November 23, 2024 @06:44PM (#42224791)
BTW, it's easy to test model's logic and truthfulness by giving it a wrong decision is if it was its, and asking to explain. Model has no memory and cannot distinguish the source of the text. 'Truthful' model should admit mistake without being asked. Likely model instead will do 'parallel construction' to support 'its' decision.

There are no comments on this comment yet.