© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 7-RESID-POST-AA · 77511 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
77511

INDEX

Explanations

hamburger

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

资金

-0.08

 Levels

-0.07

getParameter

-0.07

 новые

-0.07

 новых

-0.07

='+

-0.06

Abe

-0.06

.lift

-0.06

 shortages

-0.06

avor

-0.06

POSITIVE LOGITS

 duct

0.07

 architects

0.07

_codec

0.07

 Symbols

0.07

training

0.06

 cerv

0.06

imon

0.06

SAMPLE

0.06

xlim

0.06

ature

0.06

Activations Density 0.008%

No Known Activations