INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

UNUSED

-0.17

 DependencyProperty

-0.15

esine

-0.14

 pathMatch

-0.14

 Shack

-0.14

ieving

-0.14

anki

-0.14

suma

-0.14

 bÃ¬nh

-0.14

 HÃ¼s

-0.14

POSITIVE LOGITS

 Lesbian

0.25

 lesbian

0.24

 drag

0.24

 lesbians

0.22

 audience

0.22

 Lesb

0.22

 audiences

0.22

 solo

0.21

cab

0.21

gay

0.20

Activations Density 0.000%

No Known Activations

This feature has no known activations.