500AI
← People

Euan Ong

Source-listed: Anthropic

Record snapshot: Sep 3, 2026. Coverage and affiliations may be incomplete or historical.

Selected work

5
  1. Would this change your answer? Evaluating Explanations of LLM Behavior In The Wild with Counterfactual ExperimentsSaved credit: Contributor · 2026Explore people connected to this work →
  2. Activation Oracles: Training and Evaluating LLMs as General-Purpose Activation ExplainersSaved credit: Contributor · 2025Explore people connected to this work →
  3. Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red TeamingSaved credit: Contributor · 2025Explore people connected to this work →
  4. Image Hijacks: Adversarial Images can Control Generative Models at RuntimeSaved credit: Contributor · 2024Explore people connected to this work →
  5. Successor Heads: Recurring, Interpretable Attention Heads In The WildSaved credit: Contributor · 2024Explore people connected to this work →