INDEX

Explanations

had

np_max-act · gemini-2.0-flash

The neuron detects tokens that are decimal numeric values (i.e. numbers containing a decimal point).

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

逆

-0.07

ap

-0.07

ávající

-0.06

 practice

-0.06

Paz

-0.06

 recognizer

-0.06

 nose

-0.06

ους

-0.06

.resolution

-0.06

-management

-0.06

POSITIVE LOGITS

李

0.07

 amour

0.07

hg

0.07

 roční

0.06

baru

0.06

_CANNOT

0.06

 cử

0.06

_GPIO

0.06

 HACK

0.06

latesAutoresizingMaskIntoConstraints

0.06

Activations Density 0.054%

had

The neuron detects tokens that are decimal numeric values (i.e. numbers containing a decimal point).

No Comments

No Known Activations

had

The neuron detects tokens that are decimal numeric values (i.e. numbers containing a decimal point).

No Comments

No Known Activations