INDEX

Explanations

prepositions and phrases indicating location or inclusion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 Pent

-0.16

 abstract

-0.15

omat

-0.15

iece

-0.14

 Brands

-0.14

Icons

-0.14

 Bret

-0.13

ÑĤÐ¸Ð²Ð½Ð¾Ð³Ð¾

-0.13

 pent

-0.13

ipop

-0.13

POSITIVE LOGITS

ino

0.18

chs

0.17

rios

0.16

ulis

0.14

 Canada

0.14

meric

0.14

_firestore

0.14

ucks

0.14

áº¿

0.14

 late

0.13

Activations Density 0.062%

prepositions and phrases indicating location or inclusion

No Comments

No Known Activations