INDEX

Explanations

punctuation marks or specific formatting indicators

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

iteDatabase

-0.07

ODO

-0.06

aku

-0.06

ButtonDown

-0.06

apis

-0.06

ical

-0.06

à¥Ģà¤ķ

-0.06

Ī

-0.06

kem

-0.06

/operators

-0.06

POSITIVE LOGITS

 nouvel

0.07

ou

0.07

our

0.07

 à¤ĵ

0.06

×ķ×

0.06

ÙĪ

0.06

ãģĨ

0.06

aeda

0.06

á»ĳt

0.06

à¤ĵ

0.06

Activations Density 0.119%

punctuation marks or specific formatting indicators

No Comments

No Known Activations