INDEX

Explanations

references to years, particularly in a context related to events or data gathering

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

occo

-0.17

irut

-0.15

coon

-0.14

ho

-0.14

hetto

-0.14

uber

-0.13

Ã¡Å¾e

-0.13

busters

-0.13

aber

-0.13

POSITIVE LOGITS

ukes

0.14

Ø©

0.14

jourd

0.14

ÐµÐ²Ð¸Ñĩ

0.13

odash

0.13

ãĥ«ãĥĪ

0.13

ä¸»ä¹ī

0.13

-NLS

0.13

ÅĤu

0.13

 pens

0.12

Activations Density 0.396%

references to years, particularly in a context related to events or data gathering

No Comments

No Known Activations