INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

outil

-0.15

abbr

-0.14

ph

-0.14

inc

-0.14

–

-0.14

div

-0.13

emme

-0.13

we

-0.13

 above

-0.13

ypsum

-0.13

POSITIVE LOGITS

anga

0.18

 âĹĦ

0.17

.Err

0.14

ftype

0.14

zept

0.14

creat

0.14

ÑĮÑİ

0.13

pta

0.13

Ã´m

0.13

isque

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.