INDEX

Explanations

punctuation marks, particularly periods, commas, and questions, indicating the structure of the text

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

ãĤº

-0.06

 Åŀu

-0.06

 bergen

-0.06

ÏĥÎ¼Î¿

-0.06

::*

-0.06

.makeText

-0.06

(#)

-0.06

ï½¥

-0.06

_Tab

-0.06

@qq

-0.06

POSITIVE LOGITS

 over

0.07

ency

0.07

 versus

0.07

ionage

0.07

in

0.07

vs

0.07

 pass

0.06

 such

0.06

end

0.06

Activations Density 0.191%

punctuation marks, particularly periods, commas, and questions, indicating the structure of the text

No Comments

No Known Activations