INDEX

Explanations

references to specific events and activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

ī´

-0.16

 frags

-0.16

 cÃ©lib

-0.14

 workflows

-0.14

istol

-0.13

Holiday

-0.13

 celib

-0.13

 khÃ³a

-0.13

(~

-0.12

 Qualified

-0.12

POSITIVE LOGITS

 town

0.31

 towns

0.26

 civic

0.25

 council

0.24

 borough

0.23

 streets

0.22

 street

0.22

 community

0.21

 Switch

0.20

 Civic

0.20

Activations Density 0.014%

references to specific events and activities

No Comments

No Known Activations