© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Jacobian LensNEW

Natural Language

MAY 26 Assistant AxisJAN 26 Circuit TracerAPR 26Steer SAE Evals Exports interp-engineNEW Community Blog Privacy & Terms Contact

LLAMA3.3-70B-IT · 50-RESID-POST-GF · 7982 ｜ Neuronpedia

Home
Llama3.3-70B-IT
50-RESID-POST-GF
7982

INDEX

Explanations

over the years

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

Negative Logits

osci

-0.09

 Fletcher

-0.09

æĦı

-0.08

ÐºÐ¾ÑĢÐ¸ÑģÑĤ

-0.08

elon

-0.08

spi

-0.08

á»©t

-0.08

udu

-0.08

ourg

-0.08

Å¡ÃŃm

-0.08

POSITIVE LOGITS

 time

0.17

 years

0.16

ha

0.14

alls

0.13

leaf

0.11

ze

0.11

iew

0.11

vi

0.11

its

0.10

bite

0.10

Activations Density 0.014%

No Known Activations