INDEX

Explanations

mathematical expressions and notations related to probability processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

æ®¿

-0.18

ssi

-0.14

nock

-0.14

ogh

-0.14

reator

-0.13

arbon

-0.13

 Cypress

-0.13

arakter

-0.13

illac

-0.13

qli

-0.13

POSITIVE LOGITS

 math

0.23

math

0.20

 Math

0.20

(math

0.19

 âĦ

0.19

Math

0.18

 maths

0.18

áº¹

0.17

_math

0.17

 Cand

0.17

Activations Density 0.316%

mathematical expressions and notations related to probability processes

No Comments

No Known Activations