© 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 · 11890 ｜ Neuronpedia

Home
Llama3.3-70B-IT
50-RESID-POST-GF
11890

INDEX

Explanations

industry is

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

@$

-0.10

 spons

-0.10

iso

-0.09

Iso

-0.09

OMET

-0.09

-0.09

isl

-0.08

errick

-0.08

urn

-0.08

POSITIVE LOGITS

çļĦæĺ¯

0.22

 adalah

0.16

is

0.14

 lÃł

0.13

 ÑıÐ²Ð»ÑıÐµÑĤÑģÑı

0.13

 ÎµÎ¯Î½Î±Î¹

0.13

æĺ¯

0.12

 Ã¤r

0.11

åı«

0.11

 æĺ¯

0.11

Activations Density 0.092%

No Known Activations