INDEX

Explanations

phrases related to interactions and communications between people

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 initially

-0.16

Ð»Ð¸ÑĪÐºÐ¾Ð¼

-0.15

 COVID

-0.14

 ðŁĴ

-0.14

 convention

-0.14

âĢį

-0.14

 fully

-0.13

 everything

-0.13

ðŁĴ

-0.13

POSITIVE LOGITS

ãģ¡ãĤĩãģ£ãģ¨

0.19

 chances

0.18

 chance

0.18

interested

0.17

 interested

0.17

illet

0.17

yonel

0.16

 Interested

0.16

 interest

0.16

 ê´Ģìĭ¬

0.16

Activations Density 0.081%

phrases related to interactions and communications between people

No Comments

No Known Activations