INDEX

Explanations

references to choices and variety in games or products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

fol

-0.18

apos

-0.15

Fol

-0.14

 intermitt

-0.14

osen

-0.13

viz

-0.13

Gim

-0.13

uyu

-0.13

zend

-0.13

ook

-0.13

POSITIVE LOGITS

ç«¶

0.18

acom

0.17

 genie

0.16

0.15

 à¤¢

0.15

 competing

0.15

ITUDE

0.15

ailable

0.15

èĲ

0.14

Nga

0.14

Activations Density 0.147%

references to choices and variety in games or products

No Comments

No Known Activations