INDEX

Explanations

numbers

np_max-act · gemini-2.0-flash

The neuron activates on occurrences of the word “numbers,” i.e. references to numeric lists.

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

Car

-0.06

 contr

-0.06

Tot

-0.06

HEAD

-0.06

 respectful

-0.06

::

-0.06

 بور

-0.06

 Pope

-0.06

ateful

-0.06

POSITIVE LOGITS

ellation

0.08

 اخلاق

0.07

(userInfo

0.07

 analsex

0.07

Ξ

0.07

.getStyle

0.06

ธน

0.06

.cv

0.06

="'.$

0.06

 pohod

0.06

Activations Density 0.021%

numbers

The neuron activates on occurrences of the word “numbers,” i.e. references to numeric lists.

No Comments

No Known Activations