INDEX

Explanations

comparisons of different products and their attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

Too

-0.15

enda

-0.14

abox

-0.14

Too

-0.14

'gc

-0.13

á»«a

-0.13

Lon

-0.13

nte

-0.13

agr

-0.13

foon

-0.13

POSITIVE LOGITS

isy

0.15

 nackte

0.15

0.14

è¦ª

0.14

OfString

0.14

arella

0.13

.Rotate

0.13

illum

0.13

Activations Density 0.054%

comparisons of different products and their attributes

No Comments

No Known Activations