© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Jacobian LensNEW

Natural Language

MAY 26 Assistant AxisJAN 26 Circuit TracerAPR 26Steer SAE Evals Exports interp-engineNEW Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 15-RESID-POST-AA · 24553 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
15-RESID-POST-AA
24553

INDEX

Explanations

Scientific names

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

Negative Logits

 soukrom

-0.07

anca

-0.06

vé

-0.06

-0.06

Ef

-0.06

ビ

-0.06

Chess

-0.06

rz

-0.06

 svě

-0.06

.getBoolean

-0.06

POSITIVE LOGITS

дер

0.06

нима

0.06

 그래

0.06

택

0.06

 grind

0.06

(MenuItem

0.06

 hometown

0.06

 competitor

0.06

_shipping

0.06

(comment

0.06

Activations Density 0.008%

No Known Activations