INDEX

Explanations

adverbs and words indicating sequence

oai_token-act-pair · gemini-2.0-flash

New Auto-Interp

Configuration

fnlp/Llama-Scope-R1-Distill/400M-Slimpajama-400M-OpenR1-Math-220k/L11R

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Hzfinfdu/SlimPajama-3B and open-r1/OpenR1-Math-220k

Features

32,768

Data Type

float32

Hook Name

blocks.11.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

UAGE

-0.07

.alibaba

-0.07

omi

-0.07

ÑĩÐ¸Ð»Ð°

-0.06

arih

-0.06

SizeMode

-0.06

 WithEvents

-0.06

Ã¦kke

-0.06

×Ĺ

-0.06

CKER

-0.06

POSITIVE LOGITS

0.07

sons

0.07

 Ð²Ð¾ÑĢ

0.07

 multic

0.06

leys

0.06

)||(

0.06

lej

0.06

Dak

0.06

Bez

0.06

hatt

0.06

Activations Density 0.100%

adverbs and words indicating sequence

No Comments

No Known Activations