© 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 · 34165 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
15-RESID-POST-AA
34165

INDEX

Explanations

inspection

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

lında

-0.07

ời

-0.06

쓰

-0.06

XK

-0.06

 sanki

-0.06

/simple

-0.06

 kadar

-0.06

 noss

-0.06

 Purs

-0.06

jac

-0.06

POSITIVE LOGITS

ires

0.07

document

0.06

yen

0.06

inka

0.06

ept

0.06

 methodologies

0.06

 PrintWriter

0.06

.Document

0.06

 wire

0.06

lake

0.06

Activations Density 0.037%

No Known Activations