INDEX

Explanations

references to locations and community events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

Ã¢m

-0.17

ÑħÑĸÐ´

-0.16

Ð»ÐµÐ²

-0.15

_Api

-0.15

ographics

-0.14

åīĳ

-0.14

 Ulus

-0.14

ãĥ³ãĥĸ

-0.14

 BÃłi

-0.14

.win

-0.13

POSITIVE LOGITS

 Font

0.27

 Stock

0.26

 Full

0.24

Enc

0.23

Sim

0.23

 Thermal

0.22

 Long

0.22

 Moreno

0.22

Cul

0.22

 Imperial

0.21

Activations Density 0.092%

references to locations and community events

No Comments

No Known Activations