© 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 · 24360 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
15-RESID-POST-AA
24360

INDEX

Explanations

this

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

<Address

-0.07

닝

-0.07

ocking

-0.07

handler

-0.06

 conventions

-0.06

ريع

-0.06

Cu

-0.06

(transaction

-0.06

ehir

-0.06

 teaches

-0.06

POSITIVE LOGITS

 failed

0.07

iesz

0.07

 stroke

0.06

odash

0.06

-model

0.06

0.06

XA

0.06

predict

0.06

.childNodes

0.06

-V

0.06

Activations Density 0.195%

No Known Activations