INDEX

Explanations

significant events or turning points in time

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

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

Negative Logits

.fhir

-0.15

kÃ¶

-0.15

Ð°Ð²Ð¸

-0.14

ollo

-0.14

tright

-0.14

uced

-0.14

aben

-0.14

 è¦

-0.14

aub

-0.14

POSITIVE LOGITS

 start

0.23

 begin

0.21

 officially

0.21

end

0.21

 debut

0.20

begin

0.19

 beginning

0.19

å¼Ģå§ĭ

0.19

 official

0.19

 shift

0.17

Activations Density 0.057%

significant events or turning points in time

No Known Activations