INDEX

Explanations

terms related to immigration and immigrant experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

inning

-0.19

uld

-0.16

Ä°Y

-0.16

MBOL

-0.16

PCM

-0.15

addle

-0.15

 ****************************************************************************

-0.14

kowski

-0.14

inho

-0.14

++++++++++++++++

-0.14

POSITIVE LOGITS

igrant

0.38

igrants

0.34

ortal

0.32

ersion

0.29

unity

0.28

igration

0.27

une

0.27

Imm

0.26

unos

0.26

ersed

0.26

Activations Density 0.007%

terms related to immigration and immigrant experiences

No Comments

No Known Activations