INDEX

Explanations

keywords and phrases related to the manufacturing industry and workplace safety

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

arges

-0.15

ãģĵãĤĵãģ«

-0.14

aphore

-0.14

acades

-0.14

orio

-0.14

-0.13

lik

-0.13

oen

-0.13

commands

-0.13

 sexuales

-0.13

POSITIVE LOGITS

how

0.52

how

0.38

why

0.35

å¦Ĥä½ķ

0.28

 cÃ³mo

0.28

 what

0.28

 ways

0.27

How

0.25

 nasÄ±l

0.25

why

0.24

Activations Density 0.178%

keywords and phrases related to the manufacturing industry and workplace safety

No Comments

No Known Activations