© 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 · 24296 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
24296

INDEX

Explanations

#include

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

 held

-0.07

 다시

-0.07

-messages

-0.07

("/")

-0.06

오는

-0.06

司

-0.06

 своїх

-0.06

 hazards

-0.06

일본

-0.06

折

-0.06

POSITIVE LOGITS

 ',',

0.07

 tire

0.06

LA

0.06

 Erin

0.06

 interle

0.06

lexible

0.06

fi

0.06

_precision

0.06

ُوا

0.06

GAME

0.05

Activations Density 0.006%

No Known Activations