INDEX

Explanations

medical terminology related to symptoms and side effects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

agar

-0.18

ÐĿÐ¯

-0.14

aga

-0.14

modifiable

-0.14

ayet

-0.14

erty

-0.14

/ns

-0.14

 Ä°t

-0.14

ModelIndex

-0.13

æ³ī

-0.13

POSITIVE LOGITS

 tiener

0.15

eba

0.15

ionario

0.15

Via

0.14

Via

0.14

INV

0.14

iner

0.14

 Force

0.14

 Bulk

0.14

Inv

0.13

Activations Density 0.028%

medical terminology related to symptoms and side effects

No Comments

No Known Activations