INDEX

Explanations

phrases where something will result in negative consequences for consumers

oai_token-act-pair · gemini-2.0-flash

New Auto-Interp

Configuration

fnlp/Llama-Scope-R1-Distill/400M-Slimpajama-400M-OpenR1-Math-220k/L11R

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Hzfinfdu/SlimPajama-3B and open-r1/OpenR1-Math-220k

Features

32,768

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.07

è¡¨çİ°

-0.06

 Municip

-0.06

 Sometimes

-0.06

 sometimes

-0.06

 sequ

-0.06

Ð¾ÐºÐ°Ð·

-0.06

 turnaround

-0.06

mÃ®

-0.06

ab

-0.06

POSITIVE LOGITS

ãĥ¡ãĥ³ãĥĪ

0.07

ppe

0.06

adol

0.06

æ°ĹãģĮ

0.06

veyor

0.06

 Hearing

0.06

 Gord

0.06

iej

0.06

 Raymond

0.06

urger

0.06

Activations Density 0.016%

phrases where something will result in negative consequences for consumers

No Comments

No Known Activations