INDEX

Explanations

references to specific entities or organizations

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

 belle

-0.15

ASY

-0.15

 Provid

-0.14

ulpt

-0.14

Æ¡

-0.14

ampie

-0.13

asy

-0.13

urette

-0.13

alette

-0.12

_clk

-0.12

POSITIVE LOGITS

avez

0.22

vana

0.19

culus

0.16

 poru

0.15

ormal

0.15

sets

0.15

ivic

0.14

itos

0.14

CHED

0.14

isson

0.14

Activations Density 0.125%

references to specific entities or organizations

No Comments

No Known Activations