INDEX

Explanations

references to familial relationships and their terminology

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

Forgery

-0.17

éĻµ

-0.16

venir

-0.15

INTERFACE

-0.15

áº©m

-0.14

ksam

-0.14

dden

-0.14

Ã¥r

-0.14

.scalablytyped

-0.14

rega

-0.14

POSITIVE LOGITS

inan

0.18

ya

0.15

OOSE

0.15

 Bella

0.14

 analog

0.14

 Album

0.14

atel

0.14

yan

0.13

/Area

0.13

Activations Density 0.020%

references to familial relationships and their terminology

No Comments

No Known Activations