INDEX

Explanations

technical terminology related to formal systems and structured data management

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

assi

-0.15

/ne

-0.14

/not

-0.14

ioned

-0.13

/he

-0.12

iston

-0.12

/the

-0.12

/her

-0.12

å¤ªéĥİ

-0.12

POSITIVE LOGITS

osaur

0.15

ÑĩÐ¸Ðº

0.15

ominator

0.15

forcer

0.14

RICT

0.13

ISODE

0.13

sembl

0.13

ÑĨÐµÐ¹

0.13

isode

0.13

æľºä¼ļ

0.13

Activations Density 0.567%

technical terminology related to formal systems and structured data management

No Comments

No Known Activations