INDEX

Explanations

references to guides or guidebooks

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

ITY

-0.18

ities

-0.18

untime

-0.18

ity

-0.17

xing

-0.17

sar

-0.17

agli

-0.16

 guided

-0.16

plier

-0.16

ns

-0.15

POSITIVE LOGITS

book

0.35

posts

0.31

books

0.28

post

0.27

BOOK

0.21

ance

0.18

ëĿ¼ìĿ¸

0.18

rail

0.17

-book

0.17

posted

0.17

Activations Density 0.028%

references to guides or guidebooks

No Comments

No Known Activations