© 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 · 65891 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
23-RESID-POST-AA
65891

INDEX

Explanations

Nan

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

jvu

-0.06

Foo

-0.06

,:

-0.06

بوب

-0.06

stantiate

-0.06

 remembers

-0.06

 delimited

-0.06

 čist

-0.06

ґ

-0.06

.waitFor

-0.06

POSITIVE LOGITS

 bipolar

0.07

 sach

0.07

自動

0.07

 Nano

0.06

ура

0.06

 plunge

0.06

 bloque

0.06

ulf

0.06

 Breitbart

0.06

nano

0.06

Activations Density 0.004%

No Known Activations