INDEX

Explanations

references to film and media critiques, particularly around themes of storytelling and character development

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

uma

-0.15

gage

-0.15

unma

-0.14

material

-0.14

Material

-0.14

ÑĻ

-0.14

arme

-0.14

shore

-0.14

earer

-0.13

ÑĥÐ¼Ð°

-0.13

POSITIVE LOGITS

 homage

0.19

 remake

0.19

 callback

0.18

 Simpsons

0.17

 greatest

0.17

 Greatest

0.17

 extended

0.17

 recreation

0.16

 legitimately

0.16

 redux

0.16

Activations Density 0.299%

references to film and media critiques, particularly around themes of storytelling and character development

No Comments

No Known Activations