INDEX

Explanations

references to specific types of products, particularly in technology and design

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 Davidson

-0.14

uego

-0.14

//=

-0.14

_constants

-0.13

tps

-0.13

anoi

-0.13

autop

-0.13

BH

-0.13

ippet

-0.12

?family

-0.12

POSITIVE LOGITS

ollah

0.15

 Ø§ÙĦØ¹ÙĨ

0.14

stell

0.14

 Ø§ÙĦØ±ÙħØ²ÙĬØ©

0.14

bjerg

0.14

 thá»ĥ

0.14

swick

0.13

.dd

0.13

orget

0.13

_dd

0.13

Activations Density 0.019%

references to specific types of products, particularly in technology and design

No Comments

No Known Activations