© 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 · 7-RESID-POST-AA · 44693 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
44693

INDEX

Explanations

genomes

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

Negative Logits

Activities

-0.08

els

-0.07

cr

-0.07

 sport

-0.07

-0.06

parer

-0.06

 trabajar

-0.06

oufl

-0.06

les

-0.06

 pill

-0.06

POSITIVE LOGITS

 genome

0.17

 genomes

0.13

 Genome

0.12

OME

0.08

genome

0.08

.game

0.07

_DO

0.07

ome

0.07

 gene

0.07

 genomic

0.07

Activations Density 0.005%

No Known Activations