Allen George Ajith

Hi! I’m a second-year MSCS student (AI specialization) at NYU Courant.

I did my bachelors in Computer Science and Engineering at CUSAT.

My research is centered around mechanistic interpretability and representation learning in LLMs. I currently work with Shauli Ravfogel on two concurrent threads: scaling analysis of linear truth representations across Llama models, and understanding arithmetic operator overloading through pre-training and layer-wise activation analysis.

Previously, I’ve worked on LLM-based news sentiment analysis for FX trading, federated learning for privacy-preserving AI, link prediction in social networks, and code-mixed language modeling.

Here is my (hopefully updated) CV