INDEX

Explanations

terms related to forecasting future events and predictions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ilden

-0.15

akov

-0.15

 Feld

-0.15

ilon

-0.14

egrity

-0.14

/by

-0.13

mÃ©

-0.13

paced

-0.13

faker

-0.13

 standards

-0.13

POSITIVE LOGITS

 future

0.23

future

0.23

 futuro

0.20

_future

0.19

Future

0.18

æľªæĿ¥

0.18

 Future

0.18

-ahead

0.17

nest

0.17

uture

0.16

Activations Density 0.465%

terms related to forecasting future events and predictions

No Comments

No Known Activations