INDEX

Explanations

professional titles and affiliations related to healthcare

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

IXEL

-0.14

 dracon

-0.14

 Wool

-0.14

byt

-0.14

 nurse

-0.13

 thunder

-0.13

sez

-0.13

rous

-0.13

 sust

-0.13

azor

-0.13

POSITIVE LOGITS

PT

0.41

 Physical

0.39

PT

0.38

Physical

0.34

 physical

0.34

physical

0.31

pt

0.30

-pt

0.29

 phys

0.28

 rehabilitation

0.28

Activations Density 0.063%

professional titles and affiliations related to healthcare

No Comments

No Known Activations