INDEX

Explanations

positive attributes and conditions related to products, particularly vehicles

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

unde

-0.16

elsea

-0.15

ogne

-0.15

shr

-0.14

uien

-0.14

atel

-0.14

ICC

-0.14

issions

-0.14

shr

-0.14

POSITIVE LOGITS

regn

0.15

Ð´ÑĢÐµÑģ

0.15

§

0.15

eno

0.14

ozy

0.14

 Reactive

0.14

æ´»

0.13

=<?=$

0.13

avad

0.13

ipo

0.13

Activations Density 0.043%

positive attributes and conditions related to products, particularly vehicles

No Comments

No Known Activations