INDEX

Explanations

questions and clarifications related to data regulations and procedures

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

apat

-0.14

iddi

-0.14

tr

-0.14

orno

-0.14

aud

-0.14

orge

-0.13

 anywhere

-0.13

Å¡it

-0.13

atra

-0.13

ENSE

-0.13

POSITIVE LOGITS

 explained

0.17

 explains

0.17

 explaining

0.16

osi

0.16

ãĥįãĥ«

0.16

_definitions

0.15

explain

0.15

 exactly

0.15

Inflater

0.14

Ð²Ð¸Ñĩ

0.14

Activations Density 0.079%

questions and clarifications related to data regulations and procedures

No Comments

No Known Activations