INDEX

Explanations

references to the concept of correctness or appropriateness 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 @ 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

arine

-0.18

igel

-0.16

 Favor

-0.15

ikal

-0.15

YRO

-0.14

 better

-0.14

iren

-0.14

endency

-0.14

ary

-0.14

ishly

-0.14

POSITIVE LOGITS

 amount

0.27

-sized

0.26

 sized

0.24

 balance

0.23

-fit

0.22

/legal

0.21

 Sized

0.20

 zamanda

0.20

mix

0.19

 amounts

0.19

Activations Density 0.114%

references to the concept of correctness or appropriateness in various contexts

No Comments

No Known Activations