INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

Ì£

-0.18

gw

-0.15

 Ð¶Ðµ

-0.14

vek

-0.14

 slightly

-0.13

 somehow

-0.13

dens

-0.13

sen

-0.13

NSBundle

-0.13

fec

-0.13

POSITIVE LOGITS

 indeed

0.16

à¹Ģà¸¥à¸¢

0.15

 compared

0.15

regor

0.15

uma

0.14

 Indeed

0.14

ierarchy

0.13

erties

0.13

/high

0.13

.opendaylight

0.13

Activations Density 0.458%

No Comments

No Known Activations