© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 23-RESID-POST-AA · 30129 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
23-RESID-POST-AA
30129

INDEX

Explanations

Ph

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.23.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

MET

-0.06

 Constr

-0.06

 Mapping

-0.06

 Purpose

-0.06

our

-0.06

 salv

-0.06

 margins

-0.06

残

-0.06

 spacer

-0.06

宁

-0.06

POSITIVE LOGITS

(case

0.07

�新

0.07

.take

0.07

 upright

0.07

 basePath

0.07

ücü

0.07

.dd

0.06

vro

0.06

(calc

0.06

.sections

0.06

Activations Density 0.006%

No Known Activations