INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

eview

-0.15

wdx

-0.15

plib

-0.15

kest

-0.15

burgh

-0.15

com

-0.14

$__

-0.14

#Region

-0.14

uetooth

-0.13

ntl

-0.13

POSITIVE LOGITS

 Copyright

0.22

eval

0.21

 //--

0.20

 Â©

0.19

Â©

0.19

})(

0.18

),

0.16

Lv

0.16

https

0.16

",

0.16

Activations Density 0.000%

No Known Activations

This feature has no known activations.