© 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 · 71113 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
71113

INDEX

Explanations

for

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

 เขต

-0.06

اهرة

-0.06

-0.06

 presup

-0.06

proper

-0.06

etus

-0.06

-Regular

-0.06

 δι

-0.06

-0.06

Fo

-0.06

POSITIVE LOGITS

 decode

0.07

 deren

0.06

 pleaded

0.06

 extensive

0.06

['

0.06

енні

0.06

observations

0.06

—

0.06

He

0.06

-inch

0.06

Activations Density 0.066%

No Known Activations