INDEX

Explanations

elements related to visual imagery and photography

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

Not in Any Lists

No Comments

Negative Logits

ctor

-0.15

icens

-0.15

 latter

-0.15

 Maxim

-0.15

end

-0.14

 gene

-0.14

 being

-0.14

co

-0.14

 Cran

-0.13

 Stanton

-0.13

POSITIVE LOGITS

logfile

0.17

.SingleOrDefault

0.16

.BLL

0.14

á»ĳt

0.14

/text

0.14

.Apis

0.14

Ãłn

0.14

ÙģØ©

0.14

ÙĪØº

0.14

 Yates

0.14

Activations Density 0.052%

elements related to visual imagery and photography

No Comments

No Known Activations