INDEX

Explanations

terminology related to educational development and collaboration

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

Negative Logits

ille

-0.15

WARE

-0.14

ibe

-0.14

?key

-0.14

è²¨

-0.14

emin

-0.13

aho

-0.13

org

-0.13

angle

-0.13

 Carrier

-0.13

POSITIVE LOGITS

á»ĳt

0.14

 mastur

0.14

isposable

0.14

 Armour

0.14

leanup

0.13

ATO

0.13

atural

0.13

ãĥĮ

0.13

/epl

0.13

StartPosition

0.13

Activations Density 1.896%

terminology related to educational development and collaboration

No Known Activations