INDEX

Explanations

terms and phrases related to marketing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

oga

-0.14

 CreateTable

-0.14

est

-0.14

 generic

-0.14

 keer

-0.14

ÌĪ

-0.13

erty

-0.13

Ìĥ

-0.13

equal

-0.13

/single

-0.13

POSITIVE LOGITS

luet

0.17

edis

0.15

lyn

0.15

atoon

0.14

ifice

0.14

topl

0.14

places

0.14

ebo

0.14

paged

0.14

/mark

0.14

Activations Density 0.026%

terms and phrases related to marketing

No Comments

No Known Activations