INDEX

Explanations

artificial intelligence

np_max-act · gemini-2.0-flash

The neuron fires on tokens that occur when the assistant is talking about its own abilities or limitations—that is, self‐referential capacity (“sou capaz,” “tenho a capacidade,” “limitações,” etc.).

oai_token-act-pair · o4-mini Triggered by @xinyanhu8

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 deutschland

-0.07

ูต

-0.07

 Lahore

-0.06

れて

-0.06

微笑

-0.06

:.:.:

-0.06

 عباس

-0.06

AllowAnonymous

-0.06

，默认

-0.06

-0.05

POSITIVE LOGITS

(ast

0.07

ทย

0.07

_SMS

0.07

batis

0.07

 Department

0.06

ﺪ

0.06

getPage

0.06

.Click

0.06

 original

0.06

zik

0.06

Activations Density 0.117%

artificial intelligence

The neuron fires on tokens that occur when the assistant is talking about its own abilities or limitations—that is, self‐referential capacity (“sou capaz,” “tenho a capacidade,” “limitações,” etc.).

No Comments

No Known Activations