© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 19-RESID-POST-AA · 92017 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
19-RESID-POST-AA
92017

INDEX

Explanations

Karen

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

 отрим

-0.07

 четы

-0.07

 columns

-0.06

 две

-0.06

_selected

-0.06

 hence

-0.06

 Quincy

-0.06

.Reverse

-0.06

 isFirst

-0.06

��드

-0.06

POSITIVE LOGITS

Karen

0.09

 Karen

0.08

.kr

0.07

.decorators

0.07

ügen

0.07

0.07

(curl

0.06

oren

0.06

 trab

0.06

Ej

0.06

Activations Density 0.001%

No Known Activations