INDEX

Explanations

significant numerical data or statistics related to specific events or time periods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

à¤¼à¤°

-0.16

ech

-0.15

odes

-0.15

echa

-0.14

chin

-0.14

ovement

-0.14

dal

-0.14

anel

-0.14

esse

-0.14

ader

-0.14

POSITIVE LOGITS

 ÙħÛĮÙĦØ§Ø¯ÛĮ

0.21

Ø¡

0.18

linky

0.16

å¹´

0.16

eldo

0.15

 Ð³Ð¾Ð´Ñĥ

0.15

_BU

0.15

 ÑĢÐ¾ÐºÑĥ

0.14

 discrepan

0.14

eldon

0.13

Activations Density 0.093%

significant numerical data or statistics related to specific events or time periods

No Comments

No Known Activations