INDEX

Explanations

phrases related to protection and defense against various threats

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

elin

-0.14

æ¡Ĳ

-0.14

 EntryPoint

-0.14

ally

-0.13

ehler

-0.13

 atol

-0.13

åĵ

-0.13

renc

-0.13

_SUPPORT

-0.13

POSITIVE LOGITS

æĿ¥èĩª

0.18

/mit

0.16

 further

0.16

thood

0.15

 becoming

0.15

ogo

0.14

 dangers

0.14

 meas

0.14

ustos

0.14

odzi

0.14

Activations Density 0.083%

phrases related to protection and defense against various threats

No Comments

No Known Activations