Hadas Orgad

@OrgadHadas

Research Fellow @ Kempner Institute, Harvard | Working on AI interpretability, robustness & safety

orgadhadas.github.io

Joined April 2019

Replies Reposts Media

Pinned
Hadas Orgad
@OrgadHadas
Aug 26
Code for "Large Language Models Generate Harmful Responses Using a Distinct Mechanism, Shared Across Harm Types" is now available! It includes B-TAP, the interp method behind our work, for localizing and causally intervening on critical weights. Code + project page + paper 👇🏻
1
Hadas Orgad
@OrgadHadas
Sep 1
Come work with me! I’ll be mentoring in this fall’s @cbai_ai fellowship. If you’re interested in interpretability + AI safety, especially understanding the mechanisms behind sycophancy, deceptions, harmful generations and hallucinations, apply to my stream 👇
Cambridge Boston Alignment Initiative
@cbai_ai
Aug 31
Applications are open for the CBAI Fall Research Fellowship in AI Safety & AIxBiosecurity. Apply by September 6th at 11:59 PM EDT! 📅October 13 - December 18 💵 $15,000 stipend for 10 weeks 💰 ~$1,500+/week compute support 🏠 Housing close to our offices, arranged by CBAI
6
Hadas Orgad
@OrgadHadas
Aug 24
Announcing the keynote speakers for the Actionable Interpretability Workshop at COLM 2026! @ActInterp @boknilev @banburismus_ @ChrisGPotts @dhanya_sridhar What would you ask them?
2
Hadas Orgad
@OrgadHadas
Aug 22
Accepted to #emnlp ✅ 🎉 Read about the (non-) robustness of uncertainty probes 👇🏼
Joe Stacey
@_joestacey_
Apr 15
Replying to @_joestacey_
This work has been really fun to work on! Massive thank you my fantastic collaborators @OrgadHadas @inuikentaro @benbenhh and @NafiseSadat You can find the paper here: arxiv.org/abs/2604.11662
Hadas Orgad
@OrgadHadas
Jul 26
Accepted to COLM 2026? Consider submitting your work to the fast track at the Actionable Interpretability Workshop! @ActInterp We welcome work that advances the use of interpretability to real-world usage. Deadline: August 9 Links below 👇
1