INDEX

Explanations

references to various awards and accolades

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

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

 award

-0.32

 awards

-0.30

 Awards

-0.30

 Award

-0.29

award

-0.29

Award

-0.28

çįİ

-0.22

å¥ĸ

-0.21

_aw

-0.21

 awarded

-0.20

POSITIVE LOGITS

-winning

0.38

ing

0.29

 ceremony

0.25

 ceremonies

0.22

 Ceremony

0.22

 winning

0.21

-win

0.20

able

0.20

 Winning

0.20

win

0.20

Activations Density 0.039%

references to various awards and accolades

No Comments

No Known Activations