INDEX

Explanations

terms related to health, medical procedures, and related conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

izen

-0.15

 METH

-0.15

 Hollywood

-0.14

andas

-0.14

pur

-0.14

nee

-0.14

hart

-0.14

ÅĤa

-0.14

feito

-0.14

ita

-0.13

POSITIVE LOGITS

 such

0.22

ä¹ĭä¸Ģ

0.20

such

0.19

 SUCH

0.17

alez

0.15

nam

0.15

urge

0.15

nam

0.15

Erd

0.14

 nÃło

0.14

Activations Density 0.082%

terms related to health, medical procedures, and related conditions

No Comments

No Known Activations