INDEX

Explanations

phrases related to measurements and calculations

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

ast

-0.15

an

-0.14

au

-0.14

.habbo

-0.13

CSI

-0.13

lu

-0.13

avo

-0.12

ãĥ¼ãĤº

-0.12

ree

-0.12

ahl

-0.12

POSITIVE LOGITS

the

0.17

 actionTypes

0.15

ponsive

0.13

è¯¥

0.13

ÑĪÑĤÐ¾Ð²

0.13

raud

0.13

zept

0.13

alnÄ±z

0.13

.updateDynamic

0.12

ÅĻÃŃ

0.12

Activations Density 0.146%

phrases related to measurements and calculations

No Comments

No Known Activations