INDEX

Explanations

terms related to health care and social services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

ertz

-0.17

oola

-0.17

unker

-0.16

etric

-0.15

ROKE

-0.15

:\/\/

-0.15

xico

-0.15

mine

-0.14

roke

-0.14

etz

-0.14

POSITIVE LOGITS

 Edition

0.31

 edition

0.27

Edition

0.23

edition

0.23

çīĪ

0.22

 section

0.21

ç¯ĩ

0.20

 branch

0.19

 ÙĤØ³Ùħ

0.19

 Branch

0.19

Activations Density 0.319%

terms related to health care and social services

No Comments

No Known Activations