INDEX

Explanations

Univers

np_max-act · gemini-2.0-flash

This neuron recognizes academic affiliation phrases, especially department and university names.

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Shaw

-0.07

Raq

-0.07

 Michel

-0.07

EXAMPLE

-0.06

 numOf

-0.06

 PREFIX

-0.06

LEY

-0.06

 claws

-0.06

 hearings

-0.06

 arquivo

-0.06

POSITIVE LOGITS

 jobId

0.07

ademic

0.07

ी↵

0.07

.comboBox

0.07

Widgets

0.06

 recognizing

0.06

tableFuture

0.06

 pervasive

0.06

 ομά

0.06

 whilst

0.06

Activations Density 0.004%

Univers

This neuron recognizes academic affiliation phrases, especially department and university names.

No Comments

No Known Activations

Univers

This neuron recognizes academic affiliation phrases, especially department and university names.

No Comments

No Known Activations