INDEX

Explanations

elements related to film and television production

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

 Famous

-0.16

ettes

-0.15

.AutoScaleMode

-0.15

omen

-0.15

 Television

-0.14

 famous

-0.13

 famously

-0.13

 Lite

-0.13

 ÐºÑĥÑĢÑģ

-0.13

 animator

-0.13

POSITIVE LOGITS

 adaptation

0.16

 mult

0.16

eken

0.16

 ensemble

0.16

 buddy

0.16

ä¸ĭè½½æ¬¡æķ°

0.15

 sleeper

0.15

 thriller

0.15

hoa

0.15

umo

0.15

Activations Density 0.090%

elements related to film and television production

No Comments

No Known Activations