INDEX

Explanations

references to geographical or physical locations

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

ozem

-0.18

inges

-0.17

dsl

-0.17

ilig

-0.16

undi

-0.15

 paraph

-0.14

ologne

-0.14

 Patron

-0.14

chner

-0.13

POSITIVE LOGITS

 stand

0.21

 stands

0.20

stand

0.19

 stood

0.19

_stand

0.18

ogi

0.17

 à¤ĸà¤¡

0.17

 ç«ĭ

0.16

stood

0.16

 Äĳá»©ng

0.15

Activations Density 0.042%

references to geographical or physical locations

No Comments

No Known Activations