INDEX

Explanations

instances of the word "free" or phrases indicating no cost associated with offers or services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

etta

-0.18

WI

-0.17

ZA

-0.17

usercontent

-0.15

elm

-0.15

ê¸Ī

-0.15

ertools

-0.14

alem

-0.14

:UITableView

-0.14

ematic

-0.14

POSITIVE LOGITS

bie

0.22

bies

0.20

/free

0.20

edom

0.18

bsd

0.18

ayer

0.17

orre

0.16

AYER

0.16

zed

0.16

Ð½Ð¾Ð¶

0.15

Activations Density 0.090%

instances of the word "free" or phrases indicating no cost associated with offers or services

No Comments

No Known Activations