© 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 · 26918 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
26918

INDEX

Explanations

={

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

}}

-0.07

.False

-0.07

NJ

-0.07

 valleys

-0.07

:])

-0.06

лату

-0.06

Km

-0.06

 PIXEL

-0.06

）的

-0.06

 produkt

-0.06

POSITIVE LOGITS

 occupancy

0.06

(scale

0.06

currentColor

0.06

 enth

0.06

POL

0.06

 lubric

0.06

Subscriber

0.06

isher

0.05

squ

0.05

메

0.05

Activations Density 0.001%

No Known Activations