INDEX

Explanations

claims and admissions of responsibility or actions

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

¶Į

-0.20

ofire

-0.14

AndFeel

-0.14

orre

-0.14

leo

-0.14

tvb

-0.14

SplitOptions

-0.13

//{{

-0.13

Hallo

-0.13

esModule

-0.13

POSITIVE LOGITS

 admits

0.19

own

0.18

ack

0.18

 past

0.18

 admit

0.17

 admitted

0.17

gu

0.17

0.16

Activations Density 0.066%

claims and admissions of responsibility or actions

No Comments

No Known Activations