INDEX

Explanations

references to individuals and their roles, particularly in academic or formal contexts

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

uir

-0.20

nid

-0.15

vailability

-0.14

ondheim

-0.14

bsd

-0.13

å±ķ

-0.13

 Ø¨ÙĪØ±

-0.13

 Reform

-0.13

oire

-0.13

rchive

-0.13

POSITIVE LOGITS

ä½ľä¸º

0.21

 ä½ľ

0.16

 serve

0.16

 serving

0.15

 ingr

0.15

Hop

0.15

 serves

0.15

 sebagai

0.15

 unequal

0.14

ê°Ĳ

0.14

Activations Density 0.098%

references to individuals and their roles, particularly in academic or formal contexts

No Comments

No Known Activations