INDEX

Explanations

references to specific types of components or parts in a manufacturing or engineering context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

.sponge

-0.15

qus

-0.15

Ã¼z

-0.14

.ManyToMany

-0.14

ystone

-0.14

Ð·Ð°Ð±

-0.14

Âľ

-0.14

xeb

-0.14

 twin

-0.14

lox

-0.14

POSITIVE LOGITS

 æĻ

0.15

esser

0.15

 Carnegie

0.14

eroon

0.14

 Há»ĵ

0.14

itt

0.14

avail

0.14

 bust

0.14

 Silver

0.14

uti

0.13

Activations Density 0.166%

references to specific types of components or parts in a manufacturing or engineering context

No Comments

No Known Activations