INDEX

Explanations

part

np_max-act · gemini-2.0-flash

The neuron activates on the numeric version literal (e.g. “5.98046875”) in the file‐header comments.

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

课程

-0.07

Insets

-0.07

玲

-0.07

On

-0.07

 gravy

-0.07

WXYZ

-0.07

 earrings

-0.06

 pesticides

-0.06

Endpoints

-0.06

�

-0.06

POSITIVE LOGITS

�

0.07

_StaticFields

0.06

拍

0.06

OrNull

0.06

يار

0.06

 graphite

0.06

 orden

0.06

 Portugal

0.06

 baise

0.06

 düşür

0.06

Activations Density 0.000%

part

The neuron activates on the numeric version literal (e.g. “5.98046875”) in the file‐header comments.

No Comments

No Known Activations

part

The neuron activates on the numeric version literal (e.g. “5.98046875”) in the file‐header comments.

No Comments

No Known Activations