© 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 · 55787 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
55787

INDEX

Explanations

.Schema

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

angstrom

-0.07

沿

-0.07

 участи

-0.07

-0.07

 βασ

-0.07

 खड

-0.07

 захворю

-0.06

aktiv

-0.06

-0.06

Apellido

-0.06

POSITIVE LOGITS

 anti

0.07

 Object

0.06

_ISO

0.06

_Model

0.06

 Fresh

0.06

vision

0.06

rika

0.06

 sufficient

0.06

?>>↵

0.06

 principal

0.06

Activations Density 0.004%

No Known Activations