© 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 · 15-RESID-POST-AA · 124654 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT (Instruct)
Resid Post - 131k
15-RESID-POST-AA
124654

INDEX

Explanations

access

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_15/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.15.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

Dar

-0.07

يار

-0.06

aniu

-0.06

ecial

-0.06

�u

-0.06

 произ

-0.06

IMENT

-0.06

iped

-0.06

ываем

-0.06

$d

-0.06

POSITIVE LOGITS

 access

0.10

 Access

0.07

 proximity

0.06

 участие

0.06

 Extr

0.06

 Perez

0.06

 unin

0.06

.invalid

0.06

 sneak

0.06

輯

0.06

Activations Density 0.022%

No Known Activations