INDEX

Explanations

references to data structuring and management within a system

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

 Berry

-0.15

achat

-0.14

idge

-0.14

/TT

-0.14

Dog

-0.14

oplay

-0.14

nav

-0.13

TT

-0.13

utral

-0.13

WWW

-0.13

POSITIVE LOGITS

bins

0.17

 particular

0.16

 given

0.16

oom

0.15

ths

0.14

azo

0.14

 seasons

0.14

given

0.14

anoi

0.14

 Ticaret

0.14

Activations Density 0.263%

references to data structuring and management within a system

No Comments

No Known Activations