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

£½

-0.15

obre

-0.14

ÌĤ

-0.14

 dissent

-0.14

aggio

-0.13

chalk

-0.13

arend

-0.13

.sb

-0.13

 Pitch

-0.13

POSITIVE LOGITS

itel

0.18

oplevel

0.14

getti

0.14

ÐµÐ»Ðµ

0.14

 Fant

0.13

.googleapis

0.13

ç§ĳ

0.13

æŃ

0.13

 ìĦ

0.13

ÐĿÐĺ

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.