INDEX

Explanations

punctuation marks that denote the start of a new sentence or thought

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

oku

-0.07

utt

-0.06

icus

-0.06

ager

-0.06

inv

-0.06

 trial

-0.06

CLI

-0.06

itus

-0.06

 latest

-0.06

/stretchr

-0.05

POSITIVE LOGITS

ãĥĥãĥģ

0.07

erea

0.07

 Swinger

0.07

Gio

0.06

sup

0.06

ä½ľä¸º

0.06

asher

0.06

erot

0.06

otify

0.06

.NewRequest

0.06

Activations Density 0.060%

punctuation marks that denote the start of a new sentence or thought

No Comments

No Known Activations