INDEX

Explanations

references to automation and automated processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ÃŃcÃŃ

-0.15

mol

-0.15

 danmark

-0.14

ignum

-0.14

ekce

-0.14

rios

-0.14

fol

-0.14

illos

-0.14

canf

-0.13

 Fried

-0.13

POSITIVE LOGITS

ated

0.30

otive

0.28

aton

0.26

atically

0.25

ating

0.25

obili

0.25

obile

0.24

orphic

0.23

ATED

0.22

akers

0.22

Activations Density 0.003%

references to automation and automated processes

No Comments

No Known Activations