© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals Exports interp-engineNEWAPI Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 15-RESID-POST-AA · 34125 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
15-RESID-POST-AA
34125

INDEX

Explanations

Vertical bar

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

Tue

-0.07

�

-0.07

níkem

-0.06

_SIGN

-0.06

-0.06

ní

-0.06

robot

-0.06

.bridge

-0.06

Bloc

-0.06

Vys

-0.06

POSITIVE LOGITS

elling

0.07

anst

0.07

 disastr

0.07

उ

0.07

 edition

0.06

 dying

0.06

 dear

0.06

 اگر

0.06

 recommended

0.06

hood

0.06

Activations Density 0.013%

No Known Activations