INDEX

Explanations

phrases and elements related to structured data and notation, particularly in scientific or mathematical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

shima

-0.17

.scalablytyped

-0.16

antro

-0.15

egot

-0.14

obec

-0.14

getSingleton

-0.13

buah

-0.13

-Javadoc

-0.13

TRIES

-0.13

ÑĤÐ¾ÑĦ

-0.13

POSITIVE LOGITS

alem

0.16

podob

0.15

Ltd

0.14

 âĵĺ

0.13

Fut

0.13

.Apis

0.13

@qq

0.13

adian

0.13

 noqa

0.13

nodoc

0.13

Activations Density 0.146%

phrases and elements related to structured data and notation, particularly in scientific or mathematical contexts

No Comments

No Known Activations