INDEX

Explanations

references to awards and recognitions received by individuals or organizations

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

bgcolor

-0.13

argins

-0.13

á»ĳn

-0.13

ENTA

-0.13

syscall

-0.13

 Bedrooms

-0.12

ì©

-0.12

#ad

-0.12

åī§

-0.12

bite

-0.12

POSITIVE LOGITS

 Outstanding

0.33

 Lifetime

0.30

 lifetime

0.29

 Excellence

0.27

 outstanding

0.27

Lifetime

0.27

 recognition

0.26

 Achievement

0.26

 distinguished

0.26

 citation

0.25

Activations Density 0.082%

references to awards and recognitions received by individuals or organizations

No Comments

No Known Activations