Rauno Arike

MS student, University of Amsterdam

Joined

September 2023

Names

Rauno Arike (Preferred)

Emails

****@student.tudelft.nl (Confirmed)

,

****@student.uva.nl (Confirmed)

,

****@gmail.com (Confirmed)

Personal Links

Career & Education History

MS student

University of Amsterdam (uva.nl)

2024 – 2026

Undergrad student

Delft University of Technology (tudelft.nl)

2021 – 2024

Advisors, Relations & Conflicts

No relations added

Expertise

deep learning

,

mechanistic interpretability for neural networks

,

language model evaluations

2022 – Present

Publications

How does information access affect LLM monitors' ability to detect sabotage?
Rauno Arike, Raja Mehta Moreno, Rohan Subramani, Shubhorup Biswas, Francis Rhys Ward
- ICLR 2026 AIWILD
- Readers: Everyone
How does information access affect LLM monitors' ability to detect sabotage?
Rauno Arike, Raja Mehta Moreno, Rohan Subramani, Shubhorup Biswas, Francis Rhys Ward
- ICLR 2026 Trustworthy AI
- Readers: Everyone
How does information access affect LLM monitors' ability to detect sabotage?
Rauno Arike, Raja Mehta Moreno, Rohan Subramani, Shubhorup Biswas, Francis Rhys Ward
- Submitted to ICLR 2026
- Readers: Everyone
Interpreting Learned Feedback Patterns in Large Language Models
Luke Marks, Amir Abdullah, Clement Neo, Rauno Arike, David Krueger, Philip Torr, Fazl Barez
- NeurIPS 2024
- Readers: Everyone
Interpreting Learned Feedback Patterns in Large Language Models
Luke Marks, Amir Abdullah, Clement Neo, Rauno Arike, David Krueger, Philip Torr, Fazl Barez
- NeurIPS 2024 poster
- Readers: Everyone
Interpreting Reward Models in RLHF-Tuned Language Models Using Sparse Autoencoders
Luke Marks, Amir Abdullah, Luna Mendez, Rauno Arike, Philip Torr, Fazl Barez
- ICLR 2024 Conference Withdrawn Submission
- Readers: Everyone

Co-Authors