INDEX

Explanations

mathematical terminology and representations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

itime

-0.15

InstanceState

-0.14

\param

-0.14

stants

-0.14

clamp

-0.13

interp

-0.13

à¤£à¤¨

-0.13

axe

-0.13

_CHARSET

-0.13

onet

-0.13

POSITIVE LOGITS

 modules

0.36

 module

0.35

 Modules

0.33

 Module

0.31

Modules

0.30

modules

0.28

-module

0.28

module

0.28

-modules

0.27

Module

0.27

Activations Density 0.029%

mathematical terminology and representations

No Comments

No Known Activations