INDEX

Explanations

questions beginning with "what" that seek clarification or information

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

iculo

-0.15

ItemCount

-0.14

cq

-0.14

 Mull

-0.13

ç±

-0.13

 whom

-0.13

çŃ

-0.13

iq

-0.13

æĭħ

-0.13

POSITIVE LOGITS

berger

0.16

idot

0.14

 Hlav

0.14

emoc

0.14

ative

0.14

elic

0.14

/rss

0.13

ãĥ³ãĥĪ

0.13

PMC

0.13

/goto

0.13

Activations Density 0.061%

questions beginning with "what" that seek clarification or information

No Comments

No Known Activations