INDEX

Explanations

occurrences of the word "use" and its variations in the context of functionality or application

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

quo

-0.17

-regexp

-0.16

vla

-0.15

abbo

-0.14

rack

-0.14

splash

-0.14

sse

-0.14

tring

-0.14

amment

-0.14

)section

-0.14

POSITIVE LOGITS

 Locker

0.15

/store

0.14

ICA

0.14

eer

0.14

era

0.14

fully

0.14

 thrust

0.13

/lists

0.13

 contrasting

0.13

eric

0.13

Activations Density 0.080%

occurrences of the word "use" and its variations in the context of functionality or application

No Known Activations