INDEX

Explanations

>

np_max-act · gemini-2.0-flash

Explanation of neuron 4 behavior: the main thing this neuron does is find floating‐point numeric tokens (decimal numbers).

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

貨

-0.06

ائيل

-0.06

 Keystone

-0.06

avers

-0.06

-operation

-0.06

 بسیاری

-0.06

amus

-0.06

 أنا

-0.06

 cartesian

-0.06

POSITIVE LOGITS

до

0.07

 размер

0.07

<Renderer

0.07

 Phot

0.06

>,↵

0.06

formerly

0.06

.Right

0.06

(::

0.06

	holder

0.06

Blo

0.06

Activations Density 0.001%

>

Explanation of neuron 4 behavior: the main thing this neuron does is find floating‐point numeric tokens (decimal numbers).

No Comments

No Known Activations