INDEX

Explanations

terms and language related to programming and data processing frameworks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

iaux

-0.14

isko

-0.14

_pb

-0.14

ulen

-0.14

ziel

-0.14

Ð¯Ðº

-0.14

 Bundy

-0.13

 Rubin

-0.13

ere

-0.13

POSITIVE LOGITS

olland

0.16

ternet

0.16

affer

0.15

newInstance

0.14

 iron

0.14

 kombin

0.13

anje

0.13

Æ°Æ¡ng

0.13

å¥

0.13

åĲĲ

0.13

Activations Density 0.073%

terms and language related to programming and data processing frameworks

No Comments

No Known Activations