© 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 · 79026 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
79026

INDEX

Explanations

prepared

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

خاص

-0.07

jumbotron

-0.07

aja

-0.07

$/

-0.07

UI

-0.07

middlewares

-0.06

ाण

-0.06

ienes

-0.06

/cpu

-0.06

 vivo

-0.06

POSITIVE LOGITS

|`↵

0.07

.Override

0.07

 Panama

0.06

 Gree

0.06

 Forced

0.06

elian

0.06

 Cure

0.06

(Print

0.06

 Unsure

0.06

 jailed

0.06

Activations Density 0.002%

No Known Activations