INDEX

Explanations

references to concepts of mortality and life-and-death scenarios

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

igu

-0.15

 strav

-0.14

inz

-0.14

Ø§Ø¯Ø§

-0.14

-0.13

enis

-0.13

ç«ł

-0.13

¯

-0.13

POSITIVE LOGITS

 ready

0.18

 Plans

0.17

 plans

0.15

tempt

0.15

ready

0.15

æĭŁ

0.15

 planned

0.15

udden

0.14

urrent

0.14

issan

0.14

Activations Density 0.069%

references to concepts of mortality and life-and-death scenarios

No Comments

No Known Activations