INDEX

Explanations

questions and discussions about decision-making and change

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ÙĪØ§ÙĨ

-0.17

Å¾en

-0.16

 Nico

-0.16

lesen

-0.15

ottage

-0.15

alg

-0.15

æĳĺè¦ģ

-0.14

ÑĪÐµÐ²

-0.14

Lal

-0.14

readcr

-0.14

POSITIVE LOGITS

 depends

0.29

depends

0.23

 depend

0.22

 unclear

0.20

 Depends

0.19

 Ð·Ð°Ð²Ð¸ÑģÐ¸ÑĤ

0.18

 depended

0.18

 unknown

0.17

 determines

0.17

depend

0.17

Activations Density 0.237%

questions and discussions about decision-making and change

No Comments

No Known Activations