INDEX

Explanations

references to food-related items or establishments

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

Regards

-0.16

ÏģÎ¿Ïħ

-0.15

.nih

-0.15

ResourceManager

-0.14

Ð½Ð°Ð´

-0.14

lim

-0.13

 inex

-0.13

 Buen

-0.13

nement

-0.13

è®©æĪĳ

-0.13

POSITIVE LOGITS

tri

0.16

xo

0.15

VR

0.14

 probs

0.14

rish

0.13

 defs

0.13

 seedu

0.13

mour

0.13

ÐµÐ²ÐµÑĢ

0.13

.Persistent

0.12

Activations Density 0.050%

references to food-related items or establishments

No Comments

No Known Activations