INDEX

Explanations

medical terminology related to conditions and examinations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

 inflamm

-0.16

hcp

-0.15

nier

-0.15

Ø§ÙĬØ§

-0.14

bben

-0.14

Ð¾ÑĢÐ¾Ð¶

-0.13

elocity

-0.13

zenie

-0.13

_inline

-0.13

ombie

-0.13

POSITIVE LOGITS

 bilateral

0.19

 ÑĨÐ¸

0.18

 cafe

0.17

 viol

0.17

Ã©ri

0.17

kip

0.16

pet

0.16

 Cafe

0.16

ery

0.16

 hepat

0.16

Activations Density 0.023%

medical terminology related to conditions and examinations

No Comments

No Known Activations