INDEX

Explanations

Java package declarations and import statements

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

Ãĭ

-0.14

enco

-0.14

eras

-0.14

maze

-0.14

quette

-0.14

Ð°Ð½ÑģÐ¸

-0.14

Paw

-0.14

ruba

-0.13

enan

-0.13

 Municipal

-0.13

POSITIVE LOGITS

laughter

0.14

ModelIndex

0.13

noinspection

0.13

wei

0.13

rec

0.13

 Prospect

0.12

Ãł

0.12

logan

0.12

íĥľ

0.12

ola

0.12

Activations Density 0.034%

Java package declarations and import statements

No Comments

No Known Activations