INDEX

Explanations

references to rankings or ordinal positions

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

aml

-0.14

 fools

-0.13

ky

-0.13

Î¯Î»

-0.13

ogan

-0.13

IMS

-0.13

_manifest

-0.13

ENS

-0.13

_vlog

-0.13

.netbeans

-0.13

POSITIVE LOGITS

This

0.17

this

0.17

 This

0.16

è¿Ļ

0.16

 this

0.15

 è¿Ļ

0.14

è¿Ļä¸ª

0.14

è¿Ļä¸Ģ

0.14

iazza

0.13

These

0.13

Activations Density 0.020%

references to rankings or ordinal positions

No Comments

No Known Activations