INDEX

Explanations

instances of participation and attendance 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 @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

%A

-0.15

uyá»ĩt

-0.14

remen

-0.14

omik

-0.14

 BUFF

-0.13

 GANG

-0.13

abela

-0.13

ORITY

-0.13

Î½Î¿Î¹

-0.13

 Hlav

-0.13

POSITIVE LOGITS

 participation

1.03

 participate

0.95

 particip

0.91

 Participation

0.90

 participating

0.90

 participated

0.88

 Particip

0.88

 participates

0.88

 participant

0.82

 participants

0.77

Activations Density 0.349%

instances of participation and attendance in events or activities

No Comments

No Known Activations