INDEX

Explanations

terms related to automatic processes and conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

mbH

-0.16

ibili

-0.15

Ali

-0.14

uzu

-0.13

Writable

-0.13

angep

-0.13

ingleton

-0.13

 ÎļÎ¿Ïħ

-0.13

itou

-0.13

.digital

-0.13

POSITIVE LOGITS

 automatically

0.65

 automatic

0.63

 Automatic

0.55

automatic

0.54

 Automatically

0.52

Automatic

0.51

èĩªåĬ¨

0.51

 ìŀĲëıĻ

0.49

èĩªåĭķ

0.48

 naturally

0.47

Activations Density 0.313%

terms related to automatic processes and conditions

No Comments

No Known Activations