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

expectException

-0.14

ignon

-0.14

cente

-0.14

 Ð¿Ñĭ

-0.14

 exceptions

-0.13

omo

-0.13

 Lazar

-0.13

éĻ½

-0.13

 Concurrent

-0.13

anga

-0.13

POSITIVE LOGITS

 completion

0.43

 completing

0.39

 finishing

0.36

 Completion

0.36

completion

0.36

 completed

0.36

 finish

0.35

å®ĮæĪĲ

0.33

 Comple

0.32

 finished

0.32

Activations Density 0.017%

No Comments

No Known Activations

No Comments

No Known Activations