INDEX

Explanations

punctuation marks and formatting elements related to lists or structures in mathematical or programming contexts

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

ÑĤÐµÑĢÐ¸

-0.06

ughs

-0.06

æĦŁãģĺ

-0.06

shm

-0.06

qm

-0.06

oby

-0.06

ODB

-0.06

Ħ

-0.06

akra

-0.06

panied

-0.06

POSITIVE LOGITS

brtc

0.07

oken

0.07

ocking

0.06

isz

0.06

ren

0.06

ltra

0.06

 renewable

0.06

inear

0.06

Ð³Ð°Ð»

0.05

kus

0.05

Activations Density 0.044%

punctuation marks and formatting elements related to lists or structures in mathematical or programming contexts

No Comments

No Known Activations