INDEX

Explanations

references to the term "less" or concepts related to reduction or absence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

tero

-0.18

trash

-0.16

osaurs

-0.16

locker

-0.15

Ãºng

-0.15

ertools

-0.15

ladu

-0.15

ty

-0.15

ÑģÑĮ

-0.15

tem

-0.15

POSITIVE LOGITS

ness

0.32

nes

0.29

/un

0.23

NESS

0.20

 wonder

0.20

es

0.19

ened

0.18

(es

0.17

 wonders

0.17

/no

0.17

Activations Density 0.044%

references to the term "less" or concepts related to reduction or absence

No Comments

No Known Activations