INDEX

Explanations

medical terminology related to symptoms and side effects of various conditions and treatments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

zzo

-0.16

icals

-0.15

muÅŁ

-0.15

isay

-0.14

·»

-0.13

buc

-0.13

ewis

-0.13

vents

-0.13

meter

-0.13

.gz

-0.13

POSITIVE LOGITS

due

0.20

 Leading

0.17

may

0.17

 leading

0.16

 Gunn

0.15

ä¼´

0.15

due

0.15

 accompany

0.14

_due

0.14

 synd

0.14

Activations Density 0.094%

medical terminology related to symptoms and side effects of various conditions and treatments

No Comments

No Known Activations