INDEX

Explanations

variables, function definitions, and their corresponding data structures in code

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

 unint

-0.14

ipher

-0.14

lander

-0.13

haus

-0.13

agua

-0.13

awe

-0.13

å°ĺ

-0.13

Ø§ÙĪÙĬ

-0.13

 Ð³Ð¾ÑĤ

-0.12

lÃ©d

-0.12

POSITIVE LOGITS

ëª°

0.17

Ī

0.15

anio

0.15

olest

0.14

raÅ¾

0.14

ãĤ¢ãĥ³

0.13

 Thumb

0.13

metro

0.13

metatable

0.13

 ghosts

0.13

Activations Density 0.110%

variables, function definitions, and their corresponding data structures in code

No Comments

No Known Activations