© 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 · 15-RESID-POST-AA · 124642 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT (Instruct)
Resid Post - 131k
15-RESID-POST-AA
124642

INDEX

Explanations

CD

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_15/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.15.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

 sectarian

-0.07

ीज

-0.07

_bc

-0.07

 HEAD

-0.07

 tamil

-0.07

 folded

-0.06

 hoops

-0.06

 Hyderabad

-0.06

hik

-0.06

.until

-0.06

POSITIVE LOGITS

 ante

0.07

0.07

ULATE

0.06

.sap

0.06

Pixel

0.06

.Translate

0.06

 addSubview

0.06

 achievements

0.06

scope

0.06

FN

0.06

Activations Density 0.058%

No Known Activations