INDEX

Explanations

phrases that express negation or a lack of something

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

ouser

-0.14

è¦ı

-0.14

oom

-0.13

AAAA

-0.13

eel

-0.13

IOUS

-0.13

avery

-0.13

POSITIVE LOGITS

 simply

0.18

 merely

0.17

åıªæĺ¯

0.15

Ã¡li

0.15

ypress

0.15

ãĥĨãĥ«

0.15

mere

0.14

 resort

0.14

ëĿ½

0.14

å®¾

0.14

Activations Density 0.113%

phrases that express negation or a lack of something

No Comments

No Known Activations