© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

APIAssistant AxisNEW Circuit TracerNEW Steer SAE Evals Exports Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 3-RESID-POST-AA · 122991 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT (Instruct)
Resid Post - 131k
3-RESID-POST-AA
122991

INDEX

Explanations

mark

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_3/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.3.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

.openapi

-0.06

ою

-0.06

 Achie

-0.06

OE

-0.06

 indust

-0.06

 Pasadena

-0.06

/todo

-0.06

 detr

-0.06

OVE

-0.06

trip

-0.06

POSITIVE LOGITS

mark

0.28

MARK

0.17

 mark

0.16

Mark

0.15

-mark

0.14

marks

0.14

 watermark

0.14

 Mark

0.12

.mark

0.12

emark

0.12

Activations Density 0.009%

No Known Activations