© 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 · 7-RESID-POST-AA · 127554 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
127554

INDEX

Explanations

sec

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

Not in Any Lists

No Comments

Negative Logits

领域

-0.07

 března

-0.07

σει

-0.07

’h

-0.07

Numer

-0.06

(H

-0.06

์ท

-0.06

Regressor

-0.06

'h

-0.06

ฮ

-0.06

POSITIVE LOGITS

 constitution

0.07

ddd

0.07

.EOF

0.06

 Thời

0.06

)--

0.06

currentTime

0.06

.rf

0.06

 everywhere

0.06

orses

0.06

(timestamp

0.06

Activations Density 0.000%

No Known Activations