Scholar
Samuel Marks
Google Scholar ID: fW7yK10AAAAJ
Anthropic
large language models
AI safety
oversight
interpretability
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
2,043
H-index
13
i10-index
14
Publications
20
Co-authors
0
Publications
22 items
Would this change your answer? Evaluating Explanations of LLM Behavior In The Wild with Counterfactual Experiments
2026
Cited
0
Reading Between the Dots: Decoding Hidden Computation across Filler Tokens
2026
Cited
0
Model Spec Midtraining: Improving How Alignment Training Generalizes
2026
Cited
0
Censored LLMs as a Natural Testbed for Secret Knowledge Elicitation
2026
Cited
0
AuditBench: Evaluating Alignment Auditing Techniques on Models with Hidden Behaviors
2026
Cited
0
Activation Oracles: Training and Evaluating LLMs as General-Purpose Activation Explainers
2025
Cited
0
Auditing Games for Sandbagging
2025
Cited
0
Unsupervised decoding of encoded reasoning using language model interpretability
2025
Cited
0
Load more
