INDEX

Explanations

structured data annotations and XML attributes in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

wert

-0.17

ohn

-0.15

ega

-0.15

onto

-0.15

IMATE

-0.14

ãĥ¼ãĥģ

-0.14

ductive

-0.14

 plain

-0.14

okus

-0.14

 aktu

-0.14

POSITIVE LOGITS

ÑĥÐ»Ð°

0.16

HeaderCode

0.16

EmptyEntries

0.15

'gc

0.15

uggy

0.15

ë¥

0.15

viso

0.14

ë¢°

0.14

afone

0.14

rst

0.14

Activations Density 0.087%

structured data annotations and XML attributes in code

No Comments

No Known Activations