INDEX

Explanations

terms related to electrical systems and components

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

)((((

-0.15

ocy

-0.15

 Welfare

-0.14

elib

-0.14

#Region

-0.14

)(((

-0.14

anga

-0.13

 Refuge

-0.13

 deal

-0.13

/plugin

-0.13

POSITIVE LOGITS

wart

0.16

Ä°S

0.15

èĩ£

0.15

Ã¡nd

0.14

ÑģÑĤÑĢÐ°

0.14

smart

0.14

notes

0.14

ness

0.14

uhl

0.14

gorithms

0.14

Activations Density 0.003%

terms related to electrical systems and components

No Comments

No Known Activations