© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

APIAssistant AxisNEW Circuit TracerNEW Steer SAE Evals Exports Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 7-RESID-POST-AA · 97840 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT (Instruct)
Resid Post - 131k
7-RESID-POST-AA
97840

INDEX

Explanations

lambda calculus

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

 ersten

-0.06

 Farms

-0.06

故

-0.06

故

-0.06

롱

-0.06

OCD

-0.06

事故

-0.06

 faded

-0.06

：

-0.06

FAULT

-0.06

POSITIVE LOGITS

 cuff

0.07

tank

0.07

Movement

0.07

cih

0.07

сы

0.07

uetooth

0.07

istol

0.06

 suspended

0.06

nement

0.06

San

0.06

Activations Density 0.008%

No Known Activations