INDEX

Explanations

numerical representations and coding syntax elements related to programming logic

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

æİĽ

-0.15

 feather

-0.15

åĳ½

-0.15

ux

-0.15

 bent

-0.14

ucker

-0.14

uzz

-0.14

Za

-0.14

å°¼äºļ

-0.14

POSITIVE LOGITS

senal

0.16

ALSE

0.15

bject

0.15

odÃŃ

0.15

 ucfirst

0.14

ëĵĿ

0.14

edback

0.14

ardown

0.14

AMED

0.14

IGNAL

0.14

Activations Density 0.097%

numerical representations and coding syntax elements related to programming logic

No Comments

No Known Activations