INDEX

Explanations

coordinates in geometric or mathematical contexts

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

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ingo

-0.07

mate

-0.07

à¤¿à¤¯à¤²

-0.06

.dm

-0.06

ectar

-0.06

chein

-0.06

alley

-0.06

arin

-0.06

_codegen

-0.06

POSITIVE LOGITS

sov

0.07

ç¡

0.06

.createObject

0.06

 Ð·Ð°Ð´Ð°

0.06

kee

0.06

itals

0.06

Cob

0.06

ALSE

0.06

 Neville

0.06

loy

0.05

Activations Density 0.080%

coordinates in geometric or mathematical contexts

No Comments

No Known Activations