© 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 · 35505 ｜ Neuronpedia

Home
Llama3.3-70B-IT
50-RESID-POST-GF
35505

INDEX

Explanations

di / de / d' + noun

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

:.:

-0.09

issen

-0.09

ientos

-0.08

 Wien

-0.08

 Shawn

-0.08

fty

-0.08

Ìĥ

-0.08

èįĴ

-0.08

dek

-0.08

 Starr

-0.08

POSITIVE LOGITS

 whom

0.14

 sexe

0.11

 straw

0.10

lesh

0.10

 stature

0.10

 flesh

0.10

 orig

0.09

iÐ²

0.09

 talent

0.09

 Straw

0.09

Activations Density 0.090%

No Known Activations