INDEX

Explanations

references to specific technology or software companies and their products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

gis

-0.15

altung

-0.14

ÑĢÑĥÐ·

-0.14

rica

-0.14

 searcher

-0.14

alsy

-0.14

heimer

-0.13

uyá»ĥn

-0.13

DES

-0.13

PointerType

-0.13

POSITIVE LOGITS

.com

0.17

Inc

0.15

andon

0.14

tics

0.14

OOT

0.14

Ä±r

0.14

ĤŃ

0.14

idUser

0.14

Î¿

0.13

ooter

0.13

Activations Density 0.059%

references to specific technology or software companies and their products

No Comments

No Known Activations