INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

immel

-0.18

 eBooks

-0.18

 Westbrook

-0.14

adro

-0.14

erner

-0.14

 Forums

-0.14

 eBook

-0.14

'=

-0.14

olla

-0.13

ulkan

-0.13

POSITIVE LOGITS

 canceled

0.16

 somebody

0.14

 sort

0.14

Glo

0.14

 Cancel

0.14

 kind

0.14

nees

0.14

ICA

0.14

 atol

0.13

 Labor

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.