© 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 · 7-RESID-POST-AA · 76887 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
76887

INDEX

Explanations

Kinect

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_7/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.7.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

 youth

-0.07

充

-0.07

-0.07

_dead

-0.07

 vlas

-0.07

 lẫn

-0.07

 lunch

-0.07

.enterprise

-0.07

�

-0.06

 všechno

-0.06

POSITIVE LOGITS

 Kinect

0.10

Lights

0.06

 constitution

0.06

�

0.06

 Barbie

0.06

 moderated

0.06

 Whisper

0.06

 Image

0.06

"]
↵

0.06

 Said

0.06

Activations Density 0.002%

No Known Activations