INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

 assistir

-0.16

repid

-0.15

 storyline

-0.14

ographed

-0.14

utorials

-0.14

Ã¼le

-0.14

 pagination

-0.13

 chatte

-0.13

-scripts

-0.13

 philosoph

-0.13

POSITIVE LOGITS

 poem

0.30

 poems

0.30

 Joyce

0.24

 Pound

0.24

 poets

0.23

 poetry

0.22

 poet

0.22

 Poetry

0.22

è¯Ĺ

0.20

met

0.20

Activations Density 0.000%

No Known Activations

This feature has no known activations.