INDEX

Explanations

references to gift cards and their usage

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

 premiums

-0.15

imeo

-0.15

Ã¥n

-0.14

.borrow

-0.14

 pensions

-0.14

EmptyEntries

-0.14

 æ¥Ń

-0.14

gebn

-0.14

 LICENSE

-0.14

/trunk

-0.14

POSITIVE LOGITS

 gift

0.42

 Gift

0.40

Gift

0.32

gift

0.31

 redemption

0.28

 Rede

0.28

 redeem

0.27

rede

0.27

 gifted

0.26

 redeemed

0.26

Activations Density 0.055%

references to gift cards and their usage

No Comments

No Known Activations