INDEX

Explanations

expressions related to the concept of making or sense-making

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

aley

-0.15

uset

-0.15

anship

-0.15

owan

-0.14

yz

-0.14

_Impl

-0.14

ãĥ³ãĤ¿

-0.14

_UNUSED

-0.13

NotFoundException

-0.13

ONA

-0.13

POSITIVE LOGITS

 sense

0.49

sense

0.38

 Sense

0.37

Sense

0.35

 sentido

0.33

 senses

0.29

ense

0.24

 sens

0.22

 logical

0.21

 Logical

0.20

Activations Density 0.029%

expressions related to the concept of making or sense-making

No Comments

No Known Activations