INDEX

Explanations

references to dragons or fantastical elements in narratives

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

_lane

-0.17

Kansas

-0.16

_LANE

-0.16

OSP

-0.15

osas

-0.14

 Kansas

-0.14

etroit

-0.14

afone

-0.14

 seksi

-0.14

 maduras

-0.14

POSITIVE LOGITS

 Tooth

0.39

 dragon

0.38

 dragons

0.37

 Viking

0.36

 Vikings

0.35

 Dragon

0.34

 Dragons

0.34

 Norse

0.32

dragon

0.31

Dragon

0.30

Activations Density 0.005%

references to dragons or fantastical elements in narratives

No Comments

No Known Activations