© 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 · 20922 ｜ Neuronpedia

Home
Llama3.3-70B-IT
50-RESID-POST-GF
20922

INDEX

Explanations

eng, enz sequences

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

teen

-0.14

teenth

-0.11

turn

-0.11

enburg

-0.10

er

-0.10

erken

-0.10

ellido

-0.10

erin

-0.10

eru

-0.10

tem

-0.09

POSITIVE LOGITS

urable

0.15

issance

0.14

ils

0.14

ertainment

0.13

sylvania

0.12

 táº£ng

0.12

GLISH

0.12

ylvania

0.12

jamin

0.11

ÐµÐ´Ð¶

0.11

Activations Density 0.172%

No Known Activations