INDEX

Explanations

references to wisdom and wise individuals or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

íĻľ

-0.16

ez

-0.16

typed

-0.16

conte

-0.16

/IP

-0.15

istrovstvÃŃ

-0.15

 Gros

-0.14

liers

-0.14

iggers

-0.14

POSITIVE LOGITS

wis

0.22

Wis

0.19

fully

0.19

Wis

0.18

rana

0.17

ellaneous

0.17

acre

0.16

 Wise

0.16

 wisdom

0.16

 wise

0.15

Activations Density 0.026%

references to wisdom and wise individuals or concepts

No Comments

No Known Activations