Senthooran Rajamanoharan

Thought Branches: Interpreting LLM Reasoning Requires Resampling

Emergent Misalignment is Easy, Narrow Misalignment is Hard

Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Steering Out-of-Distribution Generalization with Concept Ablation Fine-Tuning

Eliciting Secret Knowledge from Language Models

Do I Know This Entity? Knowledge Awareness and Hallucinations in Language Models

Dense SAE Latents Are Features, Not Bugs

Are Sparse Autoencoders Useful? A Case Study in Sparse Probing

Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders