© 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 · 22782 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
22782

INDEX

Explanations

dissent

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

้ใน

-0.07

Bad

-0.07

_R

-0.07

 Uzbek

-0.06

 improbable

-0.06

('_',

-0.06

 cared

-0.06

اج

-0.06

第二

-0.06

 newX

-0.06

POSITIVE LOGITS

pipeline

0.07

ilk

0.06

 signaling

0.06

.indent

0.06

 specializing

0.06

ofs

0.06

 Political

0.06

 report

0.06

isser

0.06

.Comparator

0.06

Activations Density 0.002%

No Known Activations