INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

iet

-0.16

å¹´ä»£

-0.15

omba

-0.15

tement

-0.15

:CGRect

-0.15

uibModal

-0.14

 Annunci

-0.13

achten

-0.13

.yahoo

-0.13

Transition

-0.13

POSITIVE LOGITS

 campaign

0.29

 personalized

0.23

 personal

0.23

 Campaign

0.22

 activation

0.21

 campaigns

0.21

campaign

0.21

Campaign

0.19

 hero

0.19

 personalised

0.18

Activations Density 0.000%

No Known Activations

This feature has no known activations.