© 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 · 615 ｜ Neuronpedia

Home
Llama3.3-70B-IT
50-RESID-POST-GF
615

INDEX

Explanations

Belgrade

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

 Soviet

-0.12

 Polish

-0.12

 Eston

-0.12

 Czech

-0.11

 Estonia

-0.11

 Poland

-0.10

 Krak

-0.10

 Latvia

-0.10

äºĪ

-0.09

Å

-0.09

POSITIVE LOGITS

 Serbia

0.21

Bel

0.20

 Serbian

0.19

Mil

0.18

 Milo

0.17

.rs

0.16

Ser

0.16

 ÄĲ

0.14

 Mont

0.14

 Milan

0.14

Activations Density 0.031%

No Known Activations