INDEX

Explanations

references to corporate entities and their activities

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

olid

-0.17

eniable

-0.16

 Geile

-0.15

gebung

-0.15

 offsetof

-0.15

ideon

-0.14

 merc

-0.14

treeview

-0.14

jango

-0.14

itle

-0.13

POSITIVE LOGITS

 hind

0.16

pent

0.15

[$_

0.15

 McMaster

0.15

_REFERER

0.14

ALSE

0.14

ÐµÑģÐ¿

0.14

ÙĪØŃ

0.13

-or

0.13

ÐµÐºÐ¾Ð¼

0.13

Activations Density 0.091%

references to corporate entities and their activities

No Comments

No Known Activations