INDEX

Explanations

references to locations or places in a structured or formal context

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

plode

-0.17

slt

-0.14

rog

-0.14

GenericType

-0.14

osten

-0.14

gle

-0.14

Ø´Ùĩ

-0.13

ãĥ¼ãĥª

-0.13

igma

-0.13

rika

-0.13

POSITIVE LOGITS

ency

0.15

 Schwartz

0.15

opi

0.14

itan

0.14

ipi

0.14

anzeigen

0.13

modules

0.13

\CMS

0.13

LATED

0.13

Activations Density 0.160%

references to locations or places in a structured or formal context

No Comments

No Known Activations