INDEX

Explanations

references to earnings, income, and financial activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

eam

-0.16

enu

-0.15

ayas

-0.14

ENU

-0.14

indow

-0.14

stdClass

-0.14

ellung

-0.14

jeta

-0.14

unner

-0.14

ä¸ĢåĮº

-0.14

POSITIVE LOGITS

 sale

0.21

 selling

0.19

 sell

0.19

 sales

0.18

 sells

0.17

åįĸ

0.17

 sold

0.17

0.16

jualan

0.16

-selling

0.15

Activations Density 0.163%

references to earnings, income, and financial activities

No Comments

No Known Activations