INDEX

Explanations

elements related to adjectives and descriptive phrases in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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·Ð²Ð¸ÑĩÐ°Ð¹

-0.16

 Ð·ÐµÐ¼Ð»Ñİ

-0.14

cha

-0.13

 anytime

-0.13

åĪ°äºĨ

-0.13

ETS

-0.13

-uri

-0.13

 éĬ

-0.13

 Ãľst

-0.13

arak

-0.13

POSITIVE LOGITS

of

0.29

 cá»§a

0.24

 thereof

0.21

à¸Ĥà¸Ńà¸ĩ

0.20

OfFile

0.19

_of

0.19

of

0.19

ä¹İ

0.19

á»§a

0.18

OfWork

0.17

Activations Density 0.084%

elements related to adjectives and descriptive phrases in the text

No Comments

No Known Activations