INDEX

Explanations

relationships involving geometric shapes and their properties

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

PU

-0.07

uchs

-0.07

apat

-0.06

wn

-0.06

_BS

-0.06

aversable

-0.06

uch

-0.06

UCH

-0.06

Ø§Ø³Ø±

-0.06

uffled

-0.06

POSITIVE LOGITS

 ours

0.12

ours

0.08

mine

0.08

 main

0.07

 originals

0.07

 hers

0.07

 yours

0.07

.managed

0.07

 mine

0.07

erte

0.07

Activations Density 0.099%

relationships involving geometric shapes and their properties

No Comments

No Known Activations