INDEX

Explanations

references to specific individuals, relationships, and reviews within dialogues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ipa

-0.17

uant

-0.16

.scalablytyped

-0.16

jem

-0.15

ely

-0.15

ich

-0.15

ichert

-0.14

anter

-0.13

 Towers

-0.13

ichern

-0.13

POSITIVE LOGITS

 ÙħØ«ÙĦØ§

0.26

 Ð½Ð°Ð¿ÑĢÐ¸Ð¼ÐµÑĢ

0.19

æŁĲ

0.18

istogram

0.17

ãģ¨ãģĭ

0.17

 suddenly

0.15

owitz

0.15

 Ð½Ð°Ð¿ÑĢÐ¸ÐºÐ»Ð°Ð´

0.14

riangle

0.14

etc

0.14

Activations Density 0.403%

references to specific individuals, relationships, and reviews within dialogues

No Comments

No Known Activations