INDEX

Explanations

phrases related to candidate qualifications and attributes

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

Ð¾ÑģÑĤ

-0.15

 Mile

-0.15

lest

-0.15

planation

-0.14

obe

-0.14

 Supporting

-0.14

mile

-0.14

try

-0.14

åĬŁ

-0.13

endants

-0.13

POSITIVE LOGITS

 possess

0.32

 poss

0.32

 possesses

0.30

poss

0.29

 Poss

0.27

 bring

0.26

 brings

0.26

Poss

0.23

 possessed

0.22

 person

0.22

Activations Density 0.150%

phrases related to candidate qualifications and attributes

No Comments

No Known Activations