INDEX

Explanations

references to time durations and context in collaborative or community settings

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

 Laurent

-0.15

kro

-0.14

 then

-0.14

bert

-0.13

 Scalars

-0.13

MSR

-0.13

Alv

-0.13

bee

-0.12

POSITIVE LOGITS

.Err

0.15

apia

0.15

ubbo

0.14

ëĦĪ

0.14

_hub

0.14

apus

0.14

_INFINITY

0.14

aptive

0.14

.GetText

0.14

onga

0.13

Activations Density 0.574%

references to time durations and context in collaborative or community settings

No Comments

No Known Activations