INDEX

Explanations

phrases indicating sequence or order of events

oai_token-act-pair · gpt-4o-mini Triggered by @bot

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

ilip

-0.20

 downtown

-0.15

 Downtown

-0.14

anlÄ±

-0.14

lrt

-0.13

oding

-0.13

Ãµes

-0.13

lili

-0.13

-pt

-0.13

anko

-0.13

POSITIVE LOGITS

 next

0.39

next

0.35

preced

0.33

 preceding

0.30

 NEXT

0.29

_next

0.28

.next

0.28

	next

0.28

 ëĭ¤ìĿĮ

0.28

-next

0.27

Activations Density 0.181%

phrases indicating sequence or order of events

No Comments

No Known Activations