INDEX

Explanations

phrases indicating importance or significance in contexts involving people or objects

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

trieve

-0.15

ynes

-0.14

ä½³

-0.14

ĽĦ

-0.14

ft

-0.13

Å¾el

-0.13

 å¹

-0.13

ses

-0.13

han

-0.13

/home

-0.12

POSITIVE LOGITS

ucci

0.16

ESH

0.15

avras

0.15

UDIO

0.15

BarItem

0.14

aggable

0.14

emain

0.14

 Greenwood

0.14

äº®

0.14

anio

0.13

Activations Density 0.078%

phrases indicating importance or significance in contexts involving people or objects

No Comments

No Known Activations