© 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 · 33939 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT (Instruct)
Resid Post - 131k
15-RESID-POST-AA
33939

INDEX

Explanations

multimedia

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

CWE

-0.06

 přičemž

-0.06

 ChatColor

-0.06

’’

-0.06

.Zero

-0.05

御

-0.05

 Control

-0.05

���

-0.05

bol

-0.05

iliar

-0.05

POSITIVE LOGITS

{%

0.07

 advisable

0.07

相当

0.06

urchase

0.06

ecess

0.06

etm

0.06

 stun

0.06

 unlocks

0.06

 transcript

0.06

Wag

0.06

Activations Density 0.002%

No Known Activations