INDEX

Explanations

references to stakes and claiming interests in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ZE

-0.17

 UObject

-0.16

æ¢°

-0.15

ChangedEventArgs

-0.14

 æĿ

-0.14

antal

-0.14

adaki

-0.14

ught

-0.14

 Fruit

-0.14

DSA

-0.13

POSITIVE LOGITS

older

0.17

olin

0.16

elix

0.15

itu

0.14

erner

0.14

ame

0.14

 Hear

0.13

overn

0.13

old

0.13

gle

0.13

Activations Density 0.009%

references to stakes and claiming interests in various contexts

No Comments

No Known Activations