INDEX

Explanations

references to independence in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

ArgumentException

-0.18

iban

-0.16

ilde

-0.16

abouts

-0.16

//**↵

-0.15

ums

-0.15

abin

-0.15

 serialVersionUID

-0.15

oenix

-0.14

 Late

-0.14

POSITIVE LOGITS

uzzi

0.15

ead

0.15

/un

0.15

eneg

0.15

aisy

0.14

/self

0.14

ials

0.14

zed

0.14

 gyro

0.14

antly

0.14

Activations Density 0.026%

references to independence in various contexts

No Comments

No Known Activations