INDEX

Explanations

references to improving patient care and safety

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

ãĥ³ãĥĩãĤ£

-0.14

Å¾el

-0.14

FY

-0.14

ataka

-0.14

 reasonable

-0.13

udio

-0.13

kee

-0.13

htable

-0.13

dy

-0.13

POSITIVE LOGITS

reeze

0.17

 precious

0.15

 FindObjectOfType

0.15

ă

0.14

OCI

0.14

 your

0.14

 Male

0.13

your

0.13

_requires

0.13

Hoe

0.13

Activations Density 0.131%

references to improving patient care and safety

No Comments

No Known Activations