INDEX

Explanations

phrases indicating participation and involvement in events or activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

inton

-0.15

 Phong

-0.14

uyá»ĩt

-0.14

omik

-0.14

ABEL

-0.14

Ã©rÃ©

-0.13

%A

-0.13

Î½Î¿Î¹

-0.13

astos

-0.13

abela

-0.13

POSITIVE LOGITS

 participation

0.89

 participate

0.82

 participating

0.79

 particip

0.79

 Participation

0.78

 participated

0.78

 Particip

0.77

 participates

0.75

 participant

0.72

 PARTIC

0.69

Activations Density 0.258%

phrases indicating participation and involvement in events or activities

No Comments

No Known Activations