© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Jacobian LensNEW

Natural Language

MAY 26 Assistant AxisJAN 26 Circuit TracerAPR 26Steer SAE Evals Exports interp-engineNEW Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 19-RESID-POST-AA · 84022 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
19-RESID-POST-AA
84022

INDEX

Explanations

Abs

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

Negative Logits

pare

-0.07

от

-0.07

referrer

-0.07

 forfeiture

-0.06

 argv

-0.06

pytest

-0.06

李

-0.06

Capability

-0.06

อ

-0.06

ElementsByTagName

-0.06

POSITIVE LOGITS

Abs

0.07

 nichts

0.07

.alias

0.06

_ASS

0.06

.ingredients

0.06

ISING

0.06

ADM

0.06

 nevid

0.06

HR

0.06

abs

0.06

Activations Density 0.011%

No Known Activations