INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

 nuest

-0.16

-0.15

ÃĹ↵↵

-0.14

 libertin

-0.13

 Ã¶ld

-0.13

embed

-0.13

Ø±ÙĬØ¹

-0.13

 Ø§ÙĦÙħÙĦ

-0.13

POSITIVE LOGITS

 relevant

0.16

adero

0.15

nota

0.15

antha

0.14

cid

0.14

oter

0.14

 pointer

0.13

 extents

0.13

anning

0.13

gid

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.