INDEX

Explanations

words and phrases related to medical terminology and symptoms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

sed

-0.18

-fw

-0.16

 male

-0.16

mus

-0.14

bru

-0.14

 ÐºÐ»Ñĥ

-0.14

pus

-0.14

 Ð´Ð¾ÐºÑĥÐ¼

-0.14

ogenerated

-0.13

oproject

-0.13

POSITIVE LOGITS

 Ð·Ð°Ð±Ð¾Ð»ÐµÐ²Ð°

0.26

 Ð³ÐµÐ¼

0.23

 Ð²Ð¾ÑģÐ¿Ð°Ð»

0.23

 Ð·Ð°Ð±Ð¾Ð»ÐµÐ²Ð°Ð½Ð¸Ð¹

0.22

 Ð¸Ð½ÑĦÐµÐº

0.21

 Ð¸Ð¼Ñĥ

0.20

 Ð·Ð°Ð±Ð¾Ð»ÐµÐ²Ð°Ð½Ð¸Ñı

0.20

 Ð³Ð¾ÑĢÐ¼

0.20

 ÑģÐ¾ÑģÑĥÐ´

0.19

 Ð·Ð°ÑħÐ²Ð¾ÑĢÑİ

0.19

Activations Density 0.008%

words and phrases related to medical terminology and symptoms

No Comments

No Known Activations