INDEX

Explanations

instances of the word "look" and its variations in different forms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

-0.15

-0.14

BITS

-0.14

 dane

-0.14

Ã©ment

-0.14

ardy

-0.14

 Ð²ÑĭÐ³Ð»ÑıÐ´

-0.14

iom

-0.14

-0.13

avig

-0.13

POSITIVE LOGITS

 closely

0.34

at

0.29

 closer

0.27

Clo

0.24

Clo

0.23

 carefully

0.22

 clos

0.22

 deeper

0.20

 CLOSE

0.20

clo

0.20

Activations Density 0.040%

instances of the word "look" and its variations in different forms

No Comments

No Known Activations