INDEX

Explanations

time durations and publication details in documents

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

eldorf

-0.17

ahoma

-0.15

ober

-0.15

.ga

-0.14

\`

-0.13

bob

-0.13

ComputedStyle

-0.13

loi

-0.13

Ø¨Ø±

-0.13

subtype

-0.13

POSITIVE LOGITS

/MPL

0.16

 Uncategorized

0.16

(strpos

0.15

/english

0.14

ableView

0.14

IntegerField

0.14

ë¡¯

0.13

Î½ÏĮ

0.13

ipar

0.13

/UIKit

0.13

Activations Density 0.042%

time durations and publication details in documents

No Comments

No Known Activations