INDEX

Explanations

references to technology-related dangers and issues, particularly in the context of privacy and security

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

iams

-0.16

iox

-0.15

vie

-0.14

vay

-0.14

forc

-0.14

 Moose

-0.14

elt

-0.14

Â§Ãĥ

-0.14

 tote

-0.14

HttpException

-0.13

POSITIVE LOGITS

 explo

0.17

ammo

0.17

 disadv

0.17

ething

0.16

legg

0.15

against

0.15

icha

0.15

 undone

0.15

.GetString

0.15

 editable

0.15

Activations Density 0.083%

references to technology-related dangers and issues, particularly in the context of privacy and security

No Comments

No Known Activations