© 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 · 27-RESID-POST-AA · 9891 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
27-RESID-POST-AA
9891

INDEX

Explanations

see

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_27/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.27.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

-0.07

parate

-0.06

 format

-0.06

,params

-0.06

cales

-0.06

template

-0.06

mut

-0.06

Portland

-0.06

 cluster

-0.06

 controlId

-0.06

POSITIVE LOGITS

see

0.16

 seen

0.14

saw

0.14

 seeing

0.12

SEE

0.11

Seeing

0.11

 Seeing

0.11

See

0.11

 sees

0.11

 Seen

0.10

Activations Density 0.072%

No Known Activations