INDEX

Explanations

terms related to positive attributes and benevolent actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

etc

-0.29

etc

-0.23

çŃī

-0.19

/etc

-0.18

ritz

-0.17

 ëĵ±

-0.17

ASA

-0.15

ãģªãģ©

-0.14

atori

-0.14

 ÑįÐ»ÐµÐ¼

-0.13

POSITIVE LOGITS

 láº«n

0.45

AND

0.45

AND

0.28

 versus

0.27

vs

0.26

 ettÃ¤

0.26

as

0.23

_AND

0.23

 åĴĮ

0.22

AND

0.21

Activations Density 0.266%

terms related to positive attributes and benevolent actions

No Comments

No Known Activations