INDEX

Explanations

terms related to health outcomes and disease burden

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

-0.17

Ø²Ø´

-0.15

ãĥ¬ãĤ¹

-0.14

cloak

-0.14

.setContent

-0.14

hta

-0.13

ADATA

-0.13

ENO

-0.13

POSITIVE LOGITS

 mortality

0.31

 morb

0.29

 morality

0.28

 mortal

0.26

 Mort

0.26

mor

0.26

 complication

0.26

 late

0.25

Mor

0.24

 death

0.24

Activations Density 0.029%

terms related to health outcomes and disease burden

No Comments

No Known Activations