INDEX

Explanations

elements related to professional roles and affiliations in a corporate context

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

utor

-0.15

itou

-0.15

aki

-0.14

 trick

-0.14

ivar

-0.14

endor

-0.14

adam

-0.14

uids

-0.14

gran

-0.14

Transient

-0.13

POSITIVE LOGITS

 Partner

0.66

 partner

0.65

 partners

0.63

Partner

0.59

partner

0.57

 Partners

0.53

_partner

0.48

partners

0.47

 Ð¿Ð°ÑĢÑĤ

0.40

 partnership

0.40

Activations Density 0.097%

elements related to professional roles and affiliations in a corporate context

No Comments

No Known Activations