INDEX

Explanations

keywords and attributes related to programming, specifically in object-oriented code and data structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

 Bones

-0.15

Ú¯Ø§ÙĨÛĮ

-0.15

 Quiet

-0.14

kes

-0.14

 ÙĨÙĪÙģ

-0.14

anders

-0.14

umerator

-0.14

ÙĪÛĮØ¯

-0.14

 Ð´Ð¾Ð·

-0.13

.Android

-0.13

POSITIVE LOGITS

int

0.17

ÐµÑĢÑĤÐ¸

0.14

 Princip

0.14

 Leigh

0.14

 void

0.14

lap

0.13

ionario

0.13

unt

0.13

 expect

0.13

enting

0.13

Activations Density 0.023%

keywords and attributes related to programming, specifically in object-oriented code and data structures

No Comments

No Known Activations