INDEX

Explanations

terms related to collective entities and demographics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

allis

-0.17

ilib

-0.17

 Minerals

-0.16

tain

-0.16

uzzi

-0.15

atoes

-0.15

elib

-0.14

ato

-0.14

razione

-0.14

WORDS

-0.14

POSITIVE LOGITS

 whole

0.65

whole

0.57

 Whole

0.52

Whole

0.49

æķ´

0.31

 entirety

0.29

 ÑĨÐµÐ»

0.28

åħ¨

0.27

 entire

0.25

 ganze

0.24

Activations Density 0.034%

terms related to collective entities and demographics

No Comments

No Known Activations