INDEX

Explanations

phrases and terms associated with expiration dates and conditions related to products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

ppard

-0.16

rava

-0.14

HAV

-0.14

anko

-0.13

/types

-0.13

veh

-0.12

etÃŃ

-0.12

 Ð³ÑĥÑģÑĤ

-0.12

ä¹İ

-0.12

 viá»ĩc

-0.12

POSITIVE LOGITS

 characteristics

0.27

 built

0.27

 been

0.27

 relevance

0.25

 significance

0.25

 resemblance

0.24

 reputation

0.24

 meaning

0.24

 inherent

0.24

 tendency

0.23

Activations Density 0.274%

phrases and terms associated with expiration dates and conditions related to products

No Comments

No Known Activations