INDEX

Explanations

stop words

np_max-act · gemini-2.0-flash

The neuron is primarily triggered by numeric tokens (e.g. standalone numbers or numeric literals) in the text.

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

ันย

-0.07

cats

-0.07

TOTYPE

-0.06

Float

-0.06

Device

-0.06

flt

-0.06

enabled

-0.06

 sampled

-0.06

 ())↵

-0.06

cud

-0.06

POSITIVE LOGITS

_trace

0.07

_TRAN

0.06

----

0.06

.getSource

0.06

 рад

0.06

 manuscripts

0.06

 tram

0.06

-Ch

0.06

 PROF

0.06

 knex

0.06

Activations Density 0.045%

stop words

The neuron is primarily triggered by numeric tokens (e.g. standalone numbers or numeric literals) in the text.

No Comments

No Known Activations

stop words

The neuron is primarily triggered by numeric tokens (e.g. standalone numbers or numeric literals) in the text.

No Comments

No Known Activations