INDEX

Explanations

terms related to medical treatments and procedures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

IDX

-0.17

asan

-0.16

tsy

-0.15

pson

-0.15

upyter

-0.14

//{{

-0.14

-po

-0.13

ache

-0.13

edeki

-0.13

utschein

-0.13

POSITIVE LOGITS

ÑģÐ»Ð¸

0.16

icol

0.15

veau

0.15

voj

0.15

Broker

0.15

 defaultMessage

0.14

 çĨ

0.14

ÏħÎ³

0.14

eya

0.14

Activations Density 0.248%

terms related to medical treatments and procedures

No Comments

No Known Activations

terms related to medical treatments and procedures

No Comments

No Known Activations