© 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 · 19-RESID-POST-AA · 110908 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
19-RESID-POST-AA
110908

INDEX

Explanations

mb

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_19/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.19.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

 deter

-0.06

-General

-0.06

lararası

-0.06

粗

-0.06

质

-0.06

Star

-0.06

dropout

-0.06

 pero

-0.06

 sino

-0.06

 tedbir

-0.06

POSITIVE LOGITS

OMB

0.08

etail

0.08

amb

0.08

 posix

0.08

aming

0.07

omb

0.07

haft

0.07

AMB

0.07

 parç

0.07

.Admin

0.07

Activations Density 0.023%

No Known Activations