INDEX

Explanations

thinking

np_max-act · gemini-2.0-flash

This neuron detects mentions of specific educational or professional skills and competencies (e.g., critical thinking, problem-solving, communication, collaboration).

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

 shock

-0.07

_AD

-0.07

department

-0.07

-0.06

_ADMIN

-0.06

 scholarship

-0.06

 foolish

-0.06

sms

-0.06

HOUSE

-0.06

 merger

-0.06

POSITIVE LOGITS

 лі

0.07

 intrinsic

0.07

.good

0.06

 Palette

0.06

ucose

0.06

 Cavs

0.06

(',',$

0.06

 طرح

0.06

 Arthur

0.06

>",

0.06

Activations Density 0.010%

thinking

This neuron detects mentions of specific educational or professional skills and competencies (e.g., critical thinking, problem-solving, communication, collaboration).

No Comments

No Known Activations