INDEX

Explanations

references to applications and software components with a focus on functionality and implementation steps

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

ÐµÑģÐ¸

-0.15

eldon

-0.14

in

-0.14

angler

-0.14

 informal

-0.14

utan

-0.14

acro

-0.13

odesk

-0.13

uki

-0.13

anke

-0.13

POSITIVE LOGITS

ogle

0.17

thal

0.16

Ð»Ð¸Ñĩ

0.16

Ã¡du

0.16

lund

0.15

istrovstvÃŃ

0.15

oggle

0.14

STALL

0.14

Ä±ma

0.14

Activations Density 0.422%

references to applications and software components with a focus on functionality and implementation steps

No Comments

No Known Activations