INDEX

Explanations

descriptors and attributes related to characters and themes in epic narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

caret

-0.15

amiento

-0.14

zman

-0.14

Ix

-0.14

jes

-0.14

ODE

-0.14

aval

-0.14

Ä±s

-0.13

.digital

-0.13

modo

-0.13

POSITIVE LOGITS

RIPT

0.17

 Citation

0.17

 appropriate

0.15

aned

0.14

appropriate

0.14

citation

0.13

chyb

0.13

tvrt

0.13

strup

0.13

ully

0.13

Activations Density 0.005%

descriptors and attributes related to characters and themes in epic narratives

No Comments

No Known Activations