INDEX

Explanations

references to educational institutions and their varying states

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ouver

-0.17

isser

-0.17

ugh

-0.16

AppState

-0.15

Ã©al

-0.15

ĥ

-0.15

orer

-0.15

fox

-0.15

SEA

-0.14

.ali

-0.14

POSITIVE LOGITS

 University

0.31

University

0.26

 UNIVERSITY

0.24

 university

0.20

tro

0.20

 Univ

0.19

 universities

0.17

ëĮĢíķĻêµĲ

0.16

wide

0.16

 Universities

0.16

Activations Density 0.020%

references to educational institutions and their varying states

No Comments

No Known Activations