INDEX

Explanations

elements related to numerical data and measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

 Ð¿ÑĢÐ¾ÑĦÐµÑģÑģÐ¸Ð¾Ð½Ð°Ð»ÑĮ

-0.23

 Ð¼ÐµÑĤÐ°Ð»Ð»Ð¸

-0.21

ch

-0.20

 ÑĦÐµÐ´ÐµÑĢÐ°Ð»ÑĮ

-0.18

ello

-0.16

zh

-0.16

vyk

-0.15

 Salt

-0.15

 Czech

-0.15

POSITIVE LOGITS

ije

0.23

Ñĺ

0.23

 Ð¸Ð¼Ñĥ

0.21

ÑĻ

0.20

ÐĬ

0.20

Ñ

0.20

 zdrav

0.17

Äĳ

0.17

ÙĪØ±Ø§ÙĨ

0.17

acija

0.17

Activations Density 0.021%

elements related to numerical data and measurements

No Comments

No Known Activations