INDEX

Explanations

mathematical terminology and concepts related to probability and convergence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

igm

-0.18

 accumulated

-0.17

åĩĿ

-0.15

[:

-0.15

 à¤°à¤¹à¤¨

-0.15

coon

-0.15

ateg

-0.15

 lump

-0.14

_blocking

-0.14

 slow

-0.14

POSITIVE LOGITS

edImage

0.15

ÏĦÏĤ

0.15

ternet

0.15

 reve

0.15

:Register

0.14

ãĥŃãĥ¼

0.14

Ã¼ml

0.14

ger

0.14

uer

0.14

zon

0.14

Activations Density 0.358%

mathematical terminology and concepts related to probability and convergence

No Comments

No Known Activations