INDEX

Explanations

phrases indicating persistence or inevitability in situations

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

WND

-0.17

_simps

-0.17

adla

-0.16

vox

-0.15

ãĤ¤ãĥ¤

-0.15

AIT

-0.14

ewan

-0.14

UTO

-0.14

rowse

-0.14

zos

-0.14

POSITIVE LOGITS

 this

0.41

 thus

0.38

è¿Ļæł·

0.36

this

0.35

 asÃŃ

0.35

éĤ£æł·

0.32

thus

0.31

 THAT

0.31

 bÃ¶yle

0.31

 váºŃy

0.30

Activations Density 0.363%

phrases indicating persistence or inevitability in situations

No Comments

No Known Activations