INDEX

Explanations

technical terminology and functions related to software systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

DLL

-0.16

appen

-0.16

Yaw

-0.15

è¡

-0.15

Buffers

-0.15

æŀĿ

-0.14

DTD

-0.14

pher

-0.14

/shop

-0.14

rank

-0.14

POSITIVE LOGITS

 cloud

0.25

hyp

0.24

 clouds

0.24

cloud

0.23

 Cloud

0.23

Nic

0.21

 Flavor

0.21

 Soft

0.21

Cloud

0.21

Compute

0.21

Activations Density 0.012%

technical terminology and functions related to software systems

No Comments

No Known Activations