© 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 · 15-RESID-POST-AA · 16019 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
15-RESID-POST-AA
16019

INDEX

Explanations

sleep

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_15/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.15.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

 Incident

-0.07

 analogue

-0.06

Han

-0.06

orc

-0.06

发现

-0.06

 convex

-0.06

 ivory

-0.06

兩

-0.06

bic

-0.06

 endorsing

-0.06

POSITIVE LOGITS

 sleep

0.13

 Sleep

0.12

 sleeping

0.10

Sleep

0.10

sleep

0.09

 Sleeping

0.09

 asleep

0.08

 sleepy

0.08

LEEP

0.07

 slept

0.07

Activations Density 0.013%

No Known Activations