INDEX

Explanations

elements related to optional parameters or attributes in a coding context

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

iola

-0.15

istrat

-0.15

thouse

-0.14

 hend

-0.14

åłĤ

-0.14

roit

-0.13

ÑģÑĤÐ¸Ñĩ

-0.13

ordon

-0.13

afen

-0.13

 Qualified

-0.13

POSITIVE LOGITS

 optional

0.64

optional

0.54

 Optional

0.50

Optional

0.47

(optional

0.46

 OPTIONAL

0.43

 optionally

0.40

_optional

0.37

.optional

0.35

(Optional

0.34

Activations Density 0.090%

elements related to optional parameters or attributes in a coding context

No Comments

No Known Activations