INDEX

Explanations

the concepts and phrases associated with policies promoting safety and support for communities

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

panse

-0.14

zu

-0.13

æĪ´

-0.13

.highlight

-0.13

zoom

-0.13

IQ

-0.13

asta

-0.13

ypi

-0.13

 Kore

-0.13

.listFiles

-0.13

POSITIVE LOGITS

 supporting

0.16

 Policies

0.15

 supportive

0.15

Ã¡b

0.15

 factors

0.15

 towards

0.15

 policies

0.14

isci

0.14

 Aeros

0.14

 toward

0.14

Activations Density 0.071%

the concepts and phrases associated with policies promoting safety and support for communities

No Comments

No Known Activations