INDEX

Explanations

punctuation and formatting marks in text

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

fnlp/Llama-Scope-R1-Distill/800M-Slimpajama-0-OpenR1-Math-220k/L15R

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Hzfinfdu/SlimPajama-3B

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

ilian

-0.17

 meas

-0.14

udd

-0.14

ãģĹãĤĩ

-0.14

ally

-0.14

arians

-0.14

 digest

-0.14

ataka

-0.13

 Field

-0.13

 FIELD

-0.13

POSITIVE LOGITS

sic

0.16

.sax

0.13

@gmail

0.13

ipse

0.13

lus

0.13

LLC

0.13

readcr

0.13

.PLL

0.13

eb

0.13

Activations Density 0.397%

punctuation and formatting marks in text

No Comments

No Known Activations