INDEX

Explanations

elements and terms related to education and teaching

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

addock

-0.21

enal

-0.15

Î»ÎµÏħ

-0.15

ãĥ³ãĥĲ

-0.15

uegos

-0.15

 Canter

-0.14

ypsum

-0.14

 birisi

-0.14

leted

-0.14

ligt

-0.13

POSITIVE LOGITS

Ð°Ð½ÑĮ

0.18

nof

0.15

 Wich

0.15

 elusive

0.15

ç¥

0.15

 failing

0.15

angl

0.14

af

0.13

ottie

0.13

ëªħìĿĦ

0.13

Activations Density 0.175%

elements and terms related to education and teaching

No Comments

No Known Activations