INDEX

Explanations

references to non-profit organizations and their activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

idir

-0.18

frey

-0.15

antz

-0.15

_sdk

-0.15

ãĥĭãĥ¼

-0.14

shint

-0.14

ayas

-0.14

ÐµÑĢÐµÐ¶

-0.14

WithContext

-0.14

interopRequire

-0.13

POSITIVE LOGITS

 profit

0.66

 Profit

0.57

profit

0.56

 profits

0.52

Profit

0.52

-profit

0.51

 PROF

0.50

 prof

0.47

_profit

0.43

 Prof

0.42

Activations Density 0.021%

references to non-profit organizations and their activities

No Comments

No Known Activations