INDEX

Explanations

references to New York or associated abbreviations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

lem

-0.17

yi

-0.15

na

-0.15

 cÃ¢n

-0.15

 cÃ©lib

-0.14

overs

-0.14

DataURL

-0.14

ocator

-0.14

zÃŃ

-0.14

paren

-0.14

POSITIVE LOGITS

quist

0.25

bble

0.24

QUI

0.21

times

0.20

gren

0.19

NÃį

0.18

daily

0.18

borg

0.18

lon

0.18

togroup

0.17

Activations Density 0.017%

references to New York or associated abbreviations

No Comments

No Known Activations