INDEX

Explanations

terms related to awards and accolades in the entertainment industry

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

usercontent

-0.15

apy

-0.15

KeyType

-0.15

eldo

-0.14

#aa

-0.14

_patterns

-0.14

vangst

-0.14

ucc

-0.14

umas

-0.14

Bil

-0.14

POSITIVE LOGITS

 award

0.38

 Award

0.33

 category

0.29

 awards

0.26

 honors

0.26

award

0.25

Award

0.24

 nominee

0.24

hon

0.24

category

0.23

Activations Density 0.055%

terms related to awards and accolades in the entertainment industry

No Comments

No Known Activations