INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

colo

-0.14

ipar

-0.14

ategy

-0.14

spender

-0.14

-0.13

åºĶ

-0.13

uvre

-0.13

 blow

-0.13

Ð»Ð¾Ð¶

-0.13

POSITIVE LOGITS

 actually

0.16

alties

0.15

allon

0.14

noon

0.14

erte

0.14

actually

0.14

UIAlert

0.14

andaÅŁ

0.14

isy

0.14

 gezocht

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.