INDEX

Explanations

references to challenges and struggles, particularly in the context of size and planning

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

urr

-0.16

ped

-0.15

ahat

-0.14

peed

-0.14

calar

-0.14

stants

-0.14

eed

-0.14

clid

-0.14

pit

-0.13

andr

-0.13

POSITIVE LOGITS

ocht

0.15

end

0.15

omon

0.15

cud

0.15

tae

0.15

 Diamonds

0.14

ochen

0.14

 ebony

0.14

0.13

elah

0.13

Activations Density 0.084%

references to challenges and struggles, particularly in the context of size and planning

No Comments

No Known Activations