INDEX

Explanations

medical and health-related terminology related to symptoms and conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

.appspot

-0.15

ype

-0.14

ometer

-0.14

FromArray

-0.14

ë²¤

-0.13

(s

-0.13

 Ansi

-0.13

erus

-0.13

ephy

-0.13

ritz

-0.13

POSITIVE LOGITS

 awakeFromNib

0.16

ÄĲT

0.15

essian

0.14

ummer

0.14

inÃ§

0.13

 Trab

0.13

ddit

0.13

 nhiÃªn

0.13

Ð°Ð»Ð¾Ð²

0.13

 Mond

0.13

Activations Density 0.172%

medical and health-related terminology related to symptoms and conditions

No Comments

No Known Activations