© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals Exports interp-engineNEWAPI Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 7-RESID-POST-AA · 35272 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
35272

INDEX

Explanations

synd

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

 erosion

-0.08

اهش

-0.07

_attention

-0.07

Ｒ

-0.07

 bodily

-0.06

、何

-0.06

 remarks

-0.06

�

-0.06

 wolves

-0.06

_lhs

-0.06

POSITIVE LOGITS

 synd

0.16

 Synd

0.14

 Consortium

0.08

nd

0.08

ynn

0.07

 Costco

0.07

idend

0.07

_Do

0.07

 During

0.07

Sy

0.07

Activations Density 0.002%

No Known Activations