© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

APIAssistant AxisNEW Circuit TracerNEW Steer SAE Evals Exports Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 3-RESID-POST-AA · 121933 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT (Instruct)
Resid Post - 131k
3-RESID-POST-AA
121933

INDEX

Explanations

macrophages

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_3/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.3.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

 lớ

-0.06

 ра

-0.06

 regs

-0.06

 Việc

-0.06

olm

-0.06

Analytics

-0.06

-0.06

득

-0.06

-0.06

RegularExpression

-0.06

POSITIVE LOGITS

roph

0.12

,state

0.06

 Seth

0.06

itty

0.06

rophy

0.06

üph

0.06

iples

0.06

igail

0.06

 DECLARE

0.06

φο

0.06

Activations Density 0.005%

No Known Activations