INDEX

Explanations

punctuation marks at the start of sentences or sections

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

 latter

-0.10

Ø©

-0.09

phans

-0.09

-0.08

yssey

-0.08

-0.07

åľ°æĸ¹

-0.07

POSITIVE LOGITS

odore

0.14

atre

0.11

gether

0.09

adays

0.09

ÑįÑĤÐ¾Ð¼Ñĥ

0.09

rador

0.08

xiety

0.07

atomy

0.07

istics

0.07

ramid

0.07

Activations Density 0.103%

punctuation marks at the start of sentences or sections

No Comments

No Known Activations