© 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 · 29708 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
23-RESID-POST-AA
29708

INDEX

Explanations

sanding and abrasion

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

 experimented

-0.07

каж

-0.07

tid

-0.06

 instrumental

-0.06

λέ

-0.06

/download

-0.06

สาว

-0.06

Pil

-0.06

 Pert

-0.06

lemen

-0.06

POSITIVE LOGITS

 Falling

0.07

LayoutManager

0.07

.Dock

0.07

失

0.06

ué

0.06

 autof

0.06

0.06

 Comics

0.06

.setName

0.06

0.06

Activations Density 0.037%

No Known Activations