INDEX

Explanations

angles represented in degrees

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

nemonic

-0.07

æ¹

-0.07

ÎºÏħ

-0.07

Ø³ÙĪØ¨

-0.06

ÙĬ

-0.06

sing

-0.06

 heightFor

-0.06

TEL

-0.06

iated

-0.06

ãģģ

-0.06

POSITIVE LOGITS

.scalablytyped

0.08

elsius

0.07

ribbon

0.07

0.06

Ĥæķ°

0.06

ï¸ı

0.06

hop

0.06

illion

0.06

 Redistributions

0.06

bras

0.06

Activations Density 0.147%

angles represented in degrees

No Comments

No Known Activations