INDEX

Explanations

references to government surveillance and security issues

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

ogo

-0.14

-0.13

 Bott

-0.13

cef

-0.13

.define

-0.13

oga

-0.13

ardon

-0.12

 Corruption

-0.12

_BINARY

-0.12

Sav

-0.12

POSITIVE LOGITS

vor

0.16

arius

0.15

ÐµÐ²Ð¸Ð´

0.15

ellas

0.14

arrant

0.14

ware

0.14

 records

0.14

ToProps

0.14

 sperma

0.14

efon

0.14

Activations Density 0.096%

references to government surveillance and security issues

No Comments

No Known Activations