INDEX

Explanations

references to the self and subjective experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 themselves

-0.24

ness

-0.22

 itself

-0.21

nya

-0.18

ship

-0.18

ly

-0.18

ÙĩØ§

-0.18

ting

-0.17

weise

-0.17

taire

-0.17

POSITIVE LOGITS

/us

0.59

/her

0.36

zzo

0.30

/my

0.30

adows

0.30

 personally

0.29

adow

0.29

SELF

0.27

andering

0.26

-mÃªme

0.25

Activations Density 0.138%

references to the self and subjective experiences

No Comments

No Known Activations