Tomer Ashuach

As large language models (LLMs) are increasingly deployed in real-world applications, the need to selectively remove unwanted knowledge while preserving model utility has become paramount. Recent work has explored sparse autoencoders (SAEs) to perform precise interventions on monosemantic feature...

Humans use introspection to evaluate their understanding through private internal states inaccessible to external observers. We investigate whether large language models possess similar privileged knowledge about answer correctness, information unavailable through external observation. We train c...