© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 11-RESID-POST-AA · 77846 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
11-RESID-POST-AA
77846

INDEX

Explanations

complete

np_max-act · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.07

 virus

-0.07

 Rodriguez

-0.07

Sak

-0.07

 signals

-0.07

-0.07

-0.06

 distinguish

-0.06

Mus

-0.06

 Virus

-0.06

POSITIVE LOGITS

 complete

0.11

 completed

0.11

completed

0.10

complete

0.09

최

0.09

 Complete

0.09

 completing

0.08

완

0.08

 Chloe

0.08

cela

0.08

Activations Density 0.042%

No Known Activations