© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals Exports interp-engineNEWAPI Community Blog Privacy & Terms Contact

LLAMA3.3-70B-IT · 50-RESID-POST-GF · 15094 ｜ Neuronpedia

Home
Llama3.3-70B-IT
50-RESID-POST-GF
15094

INDEX

Explanations

actions followed by prepositions

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf

Configuration

Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt

Prompts (Dashboard)

10,000 prompts, 128 tokens each

Dataset (Dashboard)

lmsys/lmsys-chat-1m

No Configuration Found

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 thereof

-0.09

mÃ®

-0.09

autos

-0.09

osg

-0.08

-0.08

ê·¸

-0.08

 vidÃ©

-0.08

uxt

-0.08

edin

-0.08

 frontal

-0.08

POSITIVE LOGITS

umas

0.09

ï¾

0.09

zer

0.09

re

0.09

0.08

0.08

_extend

0.08

á»Ļi

0.08

OR

0.08

comm

0.08

Activations Density 0.067%

No Known Activations