INDEX

Explanations

words related to medical procedures and health complications

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

/Dk

-0.16

 artÄ±k

-0.15

aab

-0.14

icker

-0.14

oeff

-0.13

delimiter

-0.13

abez

-0.13

.raises

-0.12

initializer

-0.12

ä»Ĭå¤©

-0.12

POSITIVE LOGITS

 during

1.33

during

1.16

 durante

1.09

 During

1.07

During

1.00

 wÃ¤hrend

0.81

 bÄĽhem

0.76

 tijd

0.69

 Ø®ÙĦØ§ÙĦ

0.59

URING

0.57

Activations Density 1.496%

words related to medical procedures and health complications

No Comments

No Known Activations