INDEX

Explanations

medical and legal terminology related to procedures and risks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

rane

-0.17

asan

-0.16

 requestOptions

-0.15

eration

-0.15

Ð¸ÑĤÑĭ

-0.14

iliz

-0.14

UIAlert

-0.14

IDTH

-0.14

refs

-0.14

.twig

-0.14

POSITIVE LOGITS

 whom

0.17

 Nich

0.16

rol

0.16

kop

0.15

 young

0.14

aint

0.13

who

0.13

 willing

0.13

dar

0.13

Activations Density 0.454%

medical and legal terminology related to procedures and risks

No Comments

No Known Activations