INDEX

Explanations

phrases or sentences that pose questions or require confirmation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

it

-0.25

 theirs

-0.24

 there

-0.24

 yours

-0.24

we

-0.24

 they

-0.23

 this

-0.23

 ours

-0.23

-this

-0.23

there

-0.22

POSITIVE LOGITS

ecast

0.15

archive

0.14

coordinate

0.14

rÃ¡l

0.13

agne

0.13

accent

0.13

endregion

0.13

certificate

0.13

acomment

0.13

runtime

0.13

Activations Density 0.034%

phrases or sentences that pose questions or require confirmation

No Comments

No Known Activations