INDEX

Explanations

terms and phrases related to technical processes and instructions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Alternatively

-0.14

.RightToLeft

-0.14

Truthy

-0.14

ãģ¾ãģŁãģ¯

-0.14

 alternatively

-0.13

ÛĢ

-0.13

Ã´t

-0.13

FINITE

-0.13

 olmayan

-0.13

meli

-0.13

POSITIVE LOGITS

etc

1.48

etc

1.30

çŃī

0.99

/etc

0.89

 çŃī

0.86

 ÑĤÐ¾ÑīÐ¾

0.78

 ëĵ±

0.77

ãģªãģ©

0.73

ect

0.69

ãģªãģ©ãģ®

0.63

Activations Density 0.671%

terms and phrases related to technical processes and instructions

No Comments

No Known Activations