INDEX

Explanations

instances of the article "a" and phrases that include articles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

Ð²Ð¾ÑĢ

-0.17

istan

-0.15

illa

-0.15

mitt

-0.15

LocalizedString

-0.14

arian

-0.14

zel

-0.14

ellig

-0.14

ä¸ŃæĸĩåŃĹå¹ķ

-0.14

illas

-0.13

POSITIVE LOGITS

 legacy

0.15

 Bers

0.15

 nearby

0.15

legacy

0.14

ÏĥÎ¼Î±

0.14

echan

0.14

 Kash

0.14

reeNode

0.14

Kem

0.13

ì¹ĺë¥¼

0.13

Activations Density 0.221%

instances of the article "a" and phrases that include articles

No Comments

No Known Activations