INDEX

Explanations

references to cheering or cheerleading activities

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

lay

-0.17

elf

-0.15

ds

-0.15

AreaView

-0.15

ogue

-0.15

emean

-0.14

ward

-0.14

ysz

-0.14

loor

-0.14

POSITIVE LOGITS

 ----------------------------------------------------------------------------↵

0.15

Trait

0.14

 Crow

0.14

rst

0.14

à¤¿à¤²à¤¨

0.13

 stacks

0.13

 pile

0.13

Kam

0.13

 Russ

0.12

à¸·à¸Ń

0.12

Activations Density 0.008%

references to cheering or cheerleading activities

No Comments

No Known Activations