© 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 · 22466 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
22466

INDEX

Explanations

do

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

its

-0.07

 which

-0.07

 swaps

-0.07

lessness

-0.07

 impressions

-0.07

 파일

-0.07

 ayır

-0.07

 lateral

-0.06

ateral

-0.06

 Which

-0.06

POSITIVE LOGITS

do

0.06

 dome

0.06

 toch

0.06

(io

0.06

DJ

0.06

 chiếu

0.06

Nä

0.06

.scalablytyped

0.06

 Hồ

0.06

 Petty

0.06

Activations Density 0.026%

No Known Activations