© 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 · 24240 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
15-RESID-POST-AA
24240

INDEX

Explanations

Ch

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

.baseUrl

-0.07

(subject

-0.07

_team

-0.06

xab

-0.06

Transactions

-0.06

 orgy

-0.06

Client

-0.06

.forms

-0.06

sizes

-0.06

.Setup

-0.06

POSITIVE LOGITS

Merc

0.07

 potassium

0.07

Dup

0.07

didn

0.07

 Dudley

0.06

Clar

0.06

 meth

0.06

 prive

0.06

 đài

0.06

'd

0.06

Activations Density 0.000%

No Known Activations