INDEX

Explanations

references to cooking, recipes, and culinary-related content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

meer

-0.16

Î¯ÏĥÏī

-0.16

aukee

-0.15

=@"

-0.15

zung

-0.15

eview

-0.14

Ø§ÙĩØ±

-0.14

mÃ¼r

-0.14

 Mezi

-0.14

artisan

-0.14

POSITIVE LOGITS

ono

0.16

 padd

0.16

owl

0.15

RE

0.14

 Burnett

0.14

ussy

0.14

 tapes

0.14

 Odyssey

0.14

master

0.14

von

0.14

Activations Density 0.181%

references to cooking, recipes, and culinary-related content

No Comments

No Known Activations