INDEX

Explanations

terms related to productivity and accessibility in a work environment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

auga

-0.14

ãĥ¼ãĥĬ

-0.14

ustomer

-0.14

 Yard

-0.13

unal

-0.13

 åĲ

-0.13

ajar

-0.13

 observer

-0.13

 chung

-0.13

erald

-0.13

POSITIVE LOGITS

 anywhere

0.49

 wherever

0.48

Anywhere

0.38

 anytime

0.36

 everywhere

0.32

-any

0.27

 whenever

0.26

 mobile

0.24

 ìĸ´ëĶĶ

0.24

 Everywhere

0.23

Activations Density 0.158%

terms related to productivity and accessibility in a work environment

No Comments

No Known Activations