© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

APIAssistant AxisNEW Circuit TracerNEW Steer SAE Evals Exports Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 7-RESID-POST-AA · 86208 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT (Instruct)
Resid Post - 131k
7-RESID-POST-AA
86208

INDEX

Explanations

food

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_7/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.7.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

ética

-0.07

ICE

-0.07

ICES

-0.07

obao

-0.06

 SNAP

-0.06

map

-0.06

 đơn

-0.06

piry

-0.06

Honda

-0.06

 Roots

-0.06

POSITIVE LOGITS

 infringement

0.06

(cos

0.06

_est

0.06

 Including

0.06

 delet

0.06

.transforms

0.06

 تصمیم

0.06

販

0.06

ylland

0.06

 explos

0.06

Activations Density 0.035%

No Known Activations