INDEX

Explanations

medical and healthcare-related acronyms and terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ettle

-0.17

-0.16

form

-0.16

aires

-0.16

orny

-0.15

umbn

-0.15

ECTOR

-0.15

/or

-0.14

aire

-0.14

stown

-0.14

POSITIVE LOGITS

sWith

0.18

0.17

/DD

0.16

/OR

0.15

ADA

0.15

/lg

0.15

sing

0.15

trs

0.14

rientation

0.14

elas

0.14

Activations Density 0.919%

medical and healthcare-related acronyms and terminology

No Comments

No Known Activations