INDEX

Explanations

phrases related to healthcare and medical topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

-0.18

 ê³¼

-0.14

forman

-0.14

 Shapiro

-0.14

-0.13

 bast

-0.13

 estate

-0.13

oose

-0.13

 nostr

-0.13

POSITIVE LOGITS

oup

0.14

HEMA

0.14

lsen

0.14

 ìĶ

0.14

Ð¼ÐµÐ½Ð¸

0.14

abinet

0.13

.LayoutStyle

0.13

eries

0.13

exampleInput

0.13

ders

0.13

Activations Density 0.316%

phrases related to healthcare and medical topics

No Comments

No Known Activations