INDEX

Explanations

references to characters in superhero narratives and their transformations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

é¬¼

-0.17

mtree

-0.15

WN

-0.15

alchemy

-0.15

 Shim

-0.15

 Zombies

-0.15

angel

-0.14

 Zombie

-0.14

Cube

-0.14

tsx

-0.14

POSITIVE LOGITS

 super

0.48

 Super

0.42

 superhero

0.41

super

0.39

Super

0.37

 superheroes

0.36

DC

0.34

 SUPER

0.34

 Superman

0.33

 cape

0.33

Activations Density 0.377%

references to characters in superhero narratives and their transformations

No Comments

No Known Activations