© 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 · 7-RESID-POST-AA · 94473 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
94473

INDEX

Explanations

resin/plastic

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_7/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.7.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

FACE

-0.07

.adv

-0.07

前の

-0.07

$out

-0.06

 первого

-0.06

_CMP

-0.06

_to

-0.06

wish

-0.06

(Web

-0.06

お

-0.06

POSITIVE LOGITS

Builders

0.06

 bots

0.06

лиц

0.06

(jsonObject

0.06

模式

0.06

itemId

0.06

 tradi

0.06

�

0.06

lenir

0.06

 Anadolu

0.06

Activations Density 0.037%

No Known Activations