INDEX

Explanations

mentions of specific food items and their characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

_IOC

-0.17

 tamp

-0.17

 Herb

-0.16

weed

-0.16

Soy

-0.16

 Cecil

-0.16

ungi

-0.15

boa

-0.15

 Mushroom

-0.15

 herb

-0.15

POSITIVE LOGITS

 apple

0.39

 apples

0.39

 fruit

0.39

 Fruit

0.34

apple

0.33

fruit

0.31

 Apple

0.30

/apple

0.29

 APPLE

0.29

Apple

0.29

Activations Density 0.103%

mentions of specific food items and their characteristics

No Comments

No Known Activations