INDEX

Explanations

terms related to supernatural abilities and powers, particularly in the context of vampires

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

 Dwarf

-0.17

otron

-0.16

 Autism

-0.15

 Sheldon

-0.14

_px

-0.14

achu

-0.14

ÑģÑĤÑĢÑĥ

-0.14

 autism

-0.14

 autistic

-0.14

celand

-0.14

POSITIVE LOGITS

 vampire

0.40

 vamp

0.40

 Vampire

0.36

 vampires

0.36

acula

0.27

ampire

0.26

 blood

0.25

wer

0.25

 Buffy

0.25

 Blood

0.24

Activations Density 0.120%

terms related to supernatural abilities and powers, particularly in the context of vampires

No Comments

No Known Activations