INDEX

Explanations

references to governmental structures and key political figures

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

ohn

-0.14

uida

-0.13

 Gord

-0.13

ang

-0.13

mam

-0.13

roid

-0.13

 ÐľÐ°

-0.13

 Sand

-0.13

atom

-0.13

uet

-0.13

POSITIVE LOGITS

 SHARES

0.15

Î¿ÏħÏĤ

0.15

alin

0.15

emmel

0.15

aska

0.15

èļ

0.14

adding

0.14

 suce

0.14

 alike

0.14

GetName

0.14

Activations Density 0.122%

references to governmental structures and key political figures

No Comments

No Known Activations