INDEX

Explanations

mathematical concepts and notations related to rational and irrational numbers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

pend

-0.16

elog

-0.15

ensation

-0.15

agged

-0.15

à¸ģà¸£

-0.15

 Regents

-0.15

 Holder

-0.15

 privile

-0.14

dash

-0.14

ej

-0.14

POSITIVE LOGITS

Fle

0.17

inalg

0.16

rompt

0.16

gal

0.15

ucker

0.15

inos

0.15

nerRadius

0.15

 Å¡p

0.14

oid

0.14

tul

0.14

Activations Density 0.029%

mathematical concepts and notations related to rational and irrational numbers

No Comments

No Known Activations