INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

adaÅŁ

-0.15

 lately

-0.15

_contents

-0.14

ÑĢÐµÐ´Ð¸ÑĤ

-0.14

.cms

-0.13

esta

-0.13

 prima

-0.13

ocha

-0.13

kli

-0.13

orro

-0.13

POSITIVE LOGITS

adt

0.14

athe

0.14

 pylint

0.14

 simul

0.13

Ø§ÙĬØ©

0.13

yms

0.13

reesome

0.13

ãĤ¤ãĤº

0.13

 rubber

0.13

ipmap

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.