INDEX

Explanations

references to significant events or changes over time

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

ante

-0.15

baum

-0.15

sy

-0.15

tr

-0.15

ãĥ¬ãĥ¼

-0.14

tl

-0.14

adar

-0.14

ANTE

-0.14

tas

-0.14

 Garr

-0.14

POSITIVE LOGITS

 ìĿ´ë²Ī

0.26

ä»Ĭå¹´

0.25

 again

0.25

 today

0.23

again

0.23

 tonight

0.23

 ä»Ĭ

0.21

now

0.21

Again

0.20

 current

0.20

Activations Density 0.082%

references to significant events or changes over time

No Comments

No Known Activations