Harshavardhan NA's picture

2

Harshavardhan NA

hvardhan878

AI & ML interests

None yet

Recent Activity

authored a paper 1 day ago

Self-Anchoring Calibration Drift in Large Language Models: How Multi-Turn Conversations Reshape Model Confidence

authored a paper 1 day ago

Feature Rivalry in Sparse Autoencoder Representations: A Mechanistic Study of Uncertainty-Driven Feature Competition in LLMs

upvoted a paper 3 days ago

Feature Rivalry in Sparse Autoencoder Representations: A Mechanistic Study of Uncertainty-Driven Feature Competition in LLMs

View all activity

Organizations

None yet

authored 2 papers 1 day ago

Self-Anchoring Calibration Drift in Large Language Models: How Multi-Turn Conversations Reshape Model Confidence

Paper • 2603.01239 • Published Mar 1 • 1

Feature Rivalry in Sparse Autoencoder Representations: A Mechanistic Study of Uncertainty-Driven Feature Competition in LLMs

Paper • 2605.08149 • Published 16 days ago • 1