INDEX

Explanations

nouns and their various forms related to literature and education

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 koji

-0.23

 italiano

-0.22

“He

-0.20

"He

-0.20

 ÑıÐºÐ¸Ð¹

-0.17

 ÐºÐ¾ÑĤÐ¾ÑĢÑĭÐ¹

-0.17

 kterÃ½

-0.17

 ÙĥØ¨ÙĬØ±

-0.17

æ´ŀ

-0.17

isÃ©

-0.17

POSITIVE LOGITS

 herself

0.34

 Î±ÏħÏĦÎ®

0.27

 italiana

0.24

 latina

0.23

 ÐºÐ¾ÑĤÐ¾ÑĢÐ°Ñı

0.23

“She

0.22

 ktÃ³ra

0.22

"She

0.22

 pÃºblica

0.21

 ÐºÐ¾ÑĤÐ¾ÑĢÑĥÑİ

0.21

Activations Density 0.133%

nouns and their various forms related to literature and education

No Comments

No Known Activations