INDEX

Explanations

Code/File paths

np_max-act · gemini-2.0-flash

The neuron fires on floating-point numeric literals (decimal fractions) appearing in code or config.

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.07

_ring

-0.06

 nghi

-0.06

 کودکان

-0.06

 halo

-0.06

.setPrototypeOf

-0.06

 qué

-0.06

інки

-0.06

(rhs

-0.06

 battery

-0.06

POSITIVE LOGITS

etros

0.07

UMENT

0.07

dej

0.06

ovalo

0.06

STEM

0.06

gether

0.06

.OnClickListener

0.06

CKER

0.06

Prostit

0.06

-letter

0.06

Activations Density 0.023%

Code/File paths

The neuron fires on floating-point numeric literals (decimal fractions) appearing in code or config.

No Comments

No Known Activations