INDEX

Explanations

terms related to programming and web development

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

sey

-0.16

 Ð¡ÑĤÑĢÐ°Ð½Ð°

-0.15

sons

-0.14

ÙĪØ±Ø§ÙĨ

-0.14

dej

-0.14

inois

-0.14

ungen

-0.13

eds

-0.13

enge

-0.13

ANNEL

-0.13

POSITIVE LOGITS

endoza

0.19

isci

0.15

Rew

0.15

eum

0.14

ÑģÑĤÐ°Ð²

0.14

recognized

0.14

erialize

0.14

ViewItem

0.14

gii

0.14

ugal

0.14

Activations Density 0.003%

terms related to programming and web development

No Comments

No Known Activations