INDEX

Explanations

references to names and titles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

 Called

-0.15

unan

-0.15

 nomine

-0.14

 called

-0.14

 Ð½Ð°Ð·Ð¸Ð²Ð°

-0.14

called

-0.13

seau

-0.13

Ð½Ð¾Ð¶

-0.13

eni

-0.13

encies

-0.13

POSITIVE LOGITS

plate

0.24

plates

0.24

éĢļãĤĬ

0.23

 given

0.23

 chosen

0.22

à¤ķà¤°à¤£

0.22

 ë¶Ļ

0.21

 change

0.19

 assigned

0.19

ì§ĵ

0.19

Activations Density 0.091%

references to names and titles

No Comments

No Known Activations