© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

LLAMA3.3-70B-IT · 50-RESID-POST-GF · 35860 ｜ Neuronpedia

Home
Llama3.3-70B-IT
50-RESID-POST-GF
35860

INDEX

Explanations

years and dates

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

-0.11

-0.11

-0.11

iser

-0.10

azo

-0.10

anth

-0.09

 &#8203;&#8203;

-0.09

inear

-0.09

 inherit

-0.09

-0.09

POSITIVE LOGITS

 Ð³Ð¾Ð´Ñĥ

0.09

 ÙħÛĮÙĦØ§Ø¯ÛĮ

0.09

.ToShort

0.09

BOTTOM

0.08

âĢ³

0.08

éĶ¦

0.08

//{{

0.08

 Latter

0.08

-scalable

0.08

ÐµÐ»Ðµ

0.08

Activations Density 0.056%

No Known Activations