© 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 · 38015 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
15-RESID-POST-AA
38015

INDEX

Explanations

//===

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

_dp

-0.06

stylesheet

-0.06

_Store

-0.06

 عصر

-0.06

-0.06

	script

-0.06

čas

-0.05

 mycket

-0.05

 courage

-0.05

 Pist

-0.05

POSITIVE LOGITS

owell

0.07

RAY

0.07

(<

0.07

//===

0.07

 Meth

0.07

odem

0.07

 acclaimed

0.06

 narrower

0.06

 Nichols

0.06

Has

0.06

Activations Density 0.001%

No Known Activations