INDEX

Explanations

references to healthcare policies and their implications

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

Negative Logits

CRYPT

-0.15

ellular

-0.15

Ø¬Ø±

-0.14

kh

-0.14

vier

-0.14

bond

-0.14

 å¿

-0.14

okrat

-0.14

asiswa

-0.13

ÑĤÐ¸Ð²

-0.13

POSITIVE LOGITS

 insurance

0.38

 health

0.36

 Insurance

0.34

 Obamacare

0.34

 Health

0.33

ACA

0.33

 Affordable

0.32

insurance

0.32

 coverage

0.32

 Coverage

0.32

Activations Density 0.147%

references to healthcare policies and their implications

No Known Activations