INDEX

Explanations

references to culinary experiences and dining events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

 caffe

-0.16

 Coffee

-0.16

Coffee

-0.15

 cigaret

-0.15

 adultes

-0.14

 thirsty

-0.14

 Cotton

-0.14

fiz

-0.14

 cigars

-0.14

 mÃ¡t

-0.14

POSITIVE LOGITS

 cooking

0.44

 cooks

0.40

 kitchens

0.40

 chef

0.39

 cook

0.39

 chefs

0.39

 kitchen

0.38

 Cooking

0.37

 culinary

0.37

Cook

0.36

Activations Density 0.615%

references to culinary experiences and dining events

No Comments

No Known Activations