INDEX

Explanations

numbers and their frequencies within 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 @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

bine

-0.14

à¸Ħà¸§à¸²à¸¡à¸£

-0.14

 Karel

-0.14

cul

-0.14

elow

-0.13

fic

-0.13

.openConnection

-0.13

_TUN

-0.13

buz

-0.13

POSITIVE LOGITS

 different

0.16

Ð½Ð°Ð´

0.16

acious

0.15

Ã¡ct

0.15

ÃºÄįast

0.14

_epsilon

0.14

 altogether

0.14

acity

0.14

ëĤĺ

0.14

à¹Ģà¸Ħ

0.14

Activations Density 0.139%

numbers and their frequencies within various contexts

No Comments

No Known Activations