© 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 · 19-RESID-POST-AA · 84274 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
19-RESID-POST-AA
84274

INDEX

Explanations

is

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

 months

-0.07

-eng

-0.07

Eng

-0.07

Lifetime

-0.06

community

-0.06

(players

-0.06

 topology

-0.06

 bride

-0.06

-0.06

lify

-0.06

POSITIVE LOGITS

 Surround

0.07

Cop

0.06

 Archbishop

0.06

bew

0.06

 BÖL

0.06

릴

0.06

 beep

0.06

άβ

0.06

SCN

0.06

습

0.06

Activations Density 0.077%

No Known Activations