INDEX

Explanations

medical terminology related to brain injuries and their treatment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

SURE

-0.15

Ø¨ÙĬÙĨ

-0.14

 íĻ

-0.14

ÑŁ

-0.14

ULLET

-0.14

 Shack

-0.14

 indem

-0.14

axe

-0.13

ãģıãĤĵ

-0.13

 æ¬

-0.13

POSITIVE LOGITS

may

0.19

 rÃ©uss

0.17

may

0.16

 Pessoa

0.16

 depending

0.16

 supportive

0.16

 alone

0.16

 Lifestyle

0.16

 success

0.15

 successful

0.15

Activations Density 0.053%

medical terminology related to brain injuries and their treatment

No Comments

No Known Activations