INDEX

Explanations

phrases and terms related to numerical data and statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

esub

-0.19

 Ð¸Ð½ÑĦÐ¾ÑĢÐ¼Ð°

-0.18

eroon

-0.16

 Ð·Ð°Ð²Ð¸ÑģÐ¸Ð¼

-0.15

 Ð¸Ð½Ð´Ð¸Ð²Ð¸Ð´Ñĥ

-0.15

 Ð´Ð¾ÐºÑĥÐ¼

-0.15

 ÑĤÐ°Ð±Ð»Ð¸

-0.15

ecast

-0.15

imei

-0.15

adesh

-0.14

POSITIVE LOGITS

 Ð¼Ð°Ñı

0.20

 ÑģÐµÑĢÐµÐ´

0.20

 ÑĦÐµÐ²ÑĢÐ°Ð»Ñı

0.19

 Ð¸ÑİÐ»Ñı

0.18

 Ð¼Ð°ÑĢÑĤÐ°

0.17

 Ð°Ð²Ð³ÑĥÑģÑĤÐ°

0.17

 Ð´ÐµÐºÐ°Ð±ÑĢÑı

0.17

 Ð½Ð°ÑĩÐ°Ð»Ð°

0.17

 ÑģÐµÐ½ÑĤÑıÐ±ÑĢÑı

0.17

 mart

0.16

Activations Density 0.025%

phrases and terms related to numerical data and statistics

No Comments

No Known Activations