INDEX

Explanations

medical terms and references related to treatments and medications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

arend

-0.15

 hend

-0.15

ickey

-0.15

 Ø¹ÙĦØ§ÙĤ

-0.14

 èĩ

-0.14

ulia

-0.14

olo

-0.14

eger

-0.14

indows

-0.14

kiem

-0.14

POSITIVE LOGITS

èĢ

0.17

ãĥĪãĥ«

0.16

esz

0.15

ÐºÑĥÐ»Ñı

0.15

ESC

0.14

.avi

0.14

æĢİ

0.13

EI

0.13

LBL

0.13

.asp

0.13

Activations Density 0.001%

medical terms and references related to treatments and medications

No Comments

No Known Activations