INDEX

Explanations

medical terminology related to procedures and testing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

Criterion

-0.17

.ManyToMany

-0.14

DES

-0.14

nech

-0.14

Desktop

-0.14

 Mount

-0.14

 Vintage

-0.14

 Silver

-0.14

ocrine

-0.14

mount

-0.14

POSITIVE LOGITS

 blood

0.20

 bleeding

0.20

blood

0.19

LOOD

0.18

 Blood

0.18

Blood

0.17

Ble

0.16

 krev

0.16

ÛĮØ±Ùĩ

0.16

 ÐºÑĢÐ¾Ð²

0.16

Activations Density 0.020%

medical terminology related to procedures and testing

No Comments

No Known Activations