INDEX

Explanations

qualifications

np_max-act · gemini-2.0-flash

This neuron responds to mentions of formal regulatory or professional credential terms—words about registration, certification, qualifications, and legal acts.

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

 Trent

-0.07

 نگ

-0.07

/s

-0.06

-budget

-0.06

 mang

-0.06

Ess

-0.06

_median

-0.06

 ldap

-0.06

ibe

-0.06

pag

-0.06

POSITIVE LOGITS

 ##↵

0.07

 materi

0.07

 embarrassed

0.07

&(

0.06

eleri

0.06

 siden

0.06

 awhile

0.06

:param

0.06

 elems

0.06

Activations Density 0.039%

qualifications

This neuron responds to mentions of formal regulatory or professional credential terms—words about registration, certification, qualifications, and legal acts.

No Comments

No Known Activations