INDEX

Explanations

references to names and titles related to individuals and brands in the context of creative industries

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

ochond

-0.14

tember

-0.14

ancellor

-0.14

RefCount

-0.13

IENTATION

-0.13

ethoven

-0.13

.opendaylight

-0.12

 Dump

-0.12

å¹³æĪĲ

-0.12

#End

-0.12

POSITIVE LOGITS

 Productions

0.45

 Studios

0.43

 Designs

0.39

 Consulting

0.37

 Enterprises

0.36

 studios

0.35

 Associates

0.35

 Studio

0.34

 Communications

0.33

 Creative

0.33

Activations Density 0.539%

references to names and titles related to individuals and brands in the context of creative industries

No Comments

No Known Activations