Nils Feldhus

nfel

https://nfelnlp.github.io

AI & ML interests

Interpretability, Explainability, Natural Language Generation

Recent Activity

upvoted a collection about 1 month ago

👤 Implicit Personalization in Language Models

liked a Space about 1 month ago

aaron0eidt/ELIA

authored a paper 3 months ago

Interpreting Language Models Through Concept Descriptions: A Survey

View all activity

Organizations

liked a Space about 1 month ago

ELIA Analysis Suite

🚀

Analyze LLM outputs with various methods

liked a dataset 4 months ago

INK-USC/eli-why

Viewer • Updated Jun 11, 2025 • 13.4k • 62 • 3

liked a model 7 months ago

deepseek-ai/DeepSeek-R1-0528-Qwen3-8B

Text Generation • 8B • Updated May 29, 2025 • 466k • • 1.01k

liked 2 datasets 8 months ago

katebor/TableEval

Preview • Updated Jul 25, 2025 • 413 • 6

SynthLabsAI/PERSONA

Viewer • Updated Oct 11, 2024 • 200k • 3.48k • 18

liked a model 8 months ago

Qwen/Qwen3-1.7B

Text Generation • 2B • Updated Jul 26, 2025 • 3.37M • • 376

liked a dataset 8 months ago

pyvene/axbench-concept16k

Viewer • Updated Jan 24, 2025 • 2.27M • 108 • 4

liked 2 datasets 9 months ago

allenai/ContextEval

Preview • Updated Nov 12, 2024 • 126 • 7

TheBlueScrubs/TheBlueScrubs-v1

Preview • Updated Feb 24, 2025 • 6 • 13

liked a model 10 months ago

microsoft/Phi-4-mini-instruct

Text Generation • 4B • Updated 25 days ago • 137k • 652

liked a Space 10 months ago

AI Deadlines

⚡

593

Organize project deadlines with ease

liked a model 11 months ago

deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B

Text Generation • 2B • Updated Feb 24, 2025 • 2.3M • • 1.42k

liked a Space about 1 year ago

Open Medical-LLM Leaderboard

🥇

433

Explore and submit models for benchmarking

liked 2 models over 1 year ago

epfl-llm/meditron-70b

Text Generation • 69B • Updated Dec 7, 2023 • 196 • 259

aaditya/Llama3-OpenBioLLM-70B

Text Generation • Updated Jan 18, 2025 • 1.62k • 492

liked a Space over 1 year ago

LLM Transparency Tool

🔬

Generate interactive web apps with Streamlit

liked a Space almost 2 years ago

PECoRe

🐑

Analyze context usage in LM generations with model internals

liked 3 models almost 2 years ago