INDEX

Explanations

phrases indicating decision-making and actions related to change or progression

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

batis

-0.17

ongyang

-0.17

Successful

-0.15

 rÃ©uss

-0.15

 successful

-0.15

getClient

-0.14

 berhasil

-0.14

 successfully

-0.14

successful

-0.14

æĪĲåĬŁ

-0.14

POSITIVE LOGITS

 pursuing

0.18

 pursuit

0.17

 pursue

0.17

 rather

0.15

iglia

0.15

 Ramp

0.15

arak

0.15

 instead

0.14

.lu

0.14

Activations Density 0.122%

phrases indicating decision-making and actions related to change or progression

No Comments

No Known Activations