INDEX

Explanations

comparisons, especially those using the word 'like'

oai_token-act-pair · gemini-2.0-flash

New Auto-Interp

Configuration

fnlp/Llama-Scope-R1-Distill/400M-Slimpajama-400M-OpenR1-Math-220k/L21R

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.21.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

åłĤ

-0.08

obia

-0.07

either

-0.07

 either

-0.07

 EITHER

-0.06

ÌĤ

-0.06

 VerfÃ¼gung

-0.06

áº£nh

-0.06

')."

-0.06

 Guys

-0.06

POSITIVE LOGITS

 many

0.15

many

0.12

è®¸å¤ļ

0.12

any

0.11

 most

0.10

 others

0.10

 Many

0.09

 MANY

0.09

 elsewhere

0.09

 other

0.09

Activations Density 0.015%

comparisons, especially those using the word 'like'

No Comments

No Known Activations