INDEX

Explanations

Register

np_max-act · gemini-2.0-flash

The neuron detects occurrences of the root “regist” (e.g. register, registered, registration).

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

-0.07

cv

-0.07

aw

-0.07

Wow

-0.07

év

-0.07

 Love

-0.07

CV

-0.07

 Vision

-0.07

Haw

-0.07

 canv

-0.07

POSITIVE LOGITS

 registered

0.11

 register

0.10

 registering

0.10

 Register

0.10

registered

0.09

Register

0.09

reg

0.09

Registered

0.09

regist

0.09

 Reggie

0.09

Activations Density 0.024%

Register

The neuron detects occurrences of the root “regist” (e.g. register, registered, registration).

No Comments

No Known Activations