INDEX

Explanations

medical terminology related to treatment approvals and patient advocacy

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

idth

-0.16

gil

-0.14

 Planet

-0.14

ince

-0.14

 eros

-0.14

ouden

-0.14

aed

-0.14

ÑĢÐ¾ÑĦ

-0.14

jez

-0.14

kest

-0.13

POSITIVE LOGITS

CAR

0.31

 adopt

0.30

 Adopt

0.25

CAR

0.25

 CART

0.24

 checkpoint

0.23

 immune

0.23

 tumor

0.22

 cancer

0.21

 engineer

0.21

Activations Density 0.005%

medical terminology related to treatment approvals and patient advocacy

No Comments

No Known Activations