INDEX

Explanations

distinctive or differing characteristics among various systems or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

PIX

-0.16

AG

-0.16

 Lambert

-0.15

ag

-0.15

shr

-0.15

ject

-0.15

INE

-0.14

 lamb

-0.14

unh

-0.14

 preferably

-0.14

POSITIVE LOGITS

 because

0.20

 porque

0.19

because

0.19

 sense

0.18

sofar

0.17

ecause

0.16

åĽłä¸º

0.16

ï¼ĮåĽłä¸º

0.16

 being

0.16

 à¸ķà¸£

0.16

Activations Density 0.150%

distinctive or differing characteristics among various systems or concepts

No Comments

No Known Activations