INDEX

Explanations

scientific/academic

np_max-act · gemini-2.0-flash

The neuron responds to programming‐related identifier tokens (like method, id, column, action).

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

probability

-0.07

 Knox

-0.07

tec

-0.06

Vars

-0.06

 ulož

-0.06

 सकत

-0.06

 gram

-0.06

rock

-0.06

 Forced

-0.06

POSITIVE LOGITS

('/:

0.07

 trẻ

0.06

 ＼:

0.06

 تنظ

0.06

 září

0.06

&t

0.06

:::::::::::

0.06

 maxX

0.06

-win

0.06

etler

0.06

Activations Density 0.321%

scientific/academic

The neuron responds to programming‐related identifier tokens (like method, id, column, action).

No Comments

No Known Activations