INDEX

Explanations

references to online services and educational resources

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 online

-0.18

 anch

-0.17

online

-0.15

 Carrier

-0.15

 outbound

-0.15

Online

-0.15

tele

-0.15

lest

-0.14

 Online

-0.14

spi

-0.14

POSITIVE LOGITS

/mobile

0.22

 platform

0.20

 platforms

0.19

/Web

0.18

å¹³åı°

0.18

platform

0.17

 Ð²Ð¸ÑĤ

0.17

/mail

0.17

/apps

0.16

/cloud

0.16

Activations Density 0.077%

references to online services and educational resources

No Comments

No Known Activations