INDEX

Explanations

mathematical terms and concepts related to ranges and boundaries

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

fnlp/Llama-Scope-R1-Distill/0-Slimpajama-800M-OpenR1-Math-220k/L15R

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

open-r1/OpenR1-Math-220k

Features

32,768

Data Type

float32

Hook Name

blocks.15.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

pecific

-0.06

 ObrÃ¡zky

-0.06

ç»©

-0.06

piel

-0.06

phere

-0.06

amura

-0.06

ANNEL

-0.06

ordon

-0.06

opoulos

-0.06

untas

-0.06

POSITIVE LOGITS

 practical

0.08

 rounding

0.07

Ð°Ð»Ñİ

0.07

 Practical

0.06

 Chick

0.06

 toler

0.06

 close

0.06

jou

0.06

 Nile

0.06

_tolerance

0.06

Activations Density 0.030%

mathematical terms and concepts related to ranges and boundaries

No Comments

No Known Activations