© 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 · 60446 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT (Instruct)
Resid Post - 131k
7-RESID-POST-AA
60446

INDEX

Explanations

medical terms

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

界

-0.07

 ма

-0.07

dd

-0.07

 northwest

-0.06

ường

-0.06

Vy

-0.06

лини

-0.06

"].(

-0.06

vu

-0.06

大

-0.06

POSITIVE LOGITS

 mutated

0.07

\Input

0.06

_FETCH

0.06

/OR

0.06

계획

0.06

GOR

0.06

 Бор

0.06

.setPassword

0.05

attention

0.05

getWidth

0.05

Activations Density 0.272%

No Known Activations