INDEX

Explanations

)

np_max-act · gemini-2.0-flash

The neuron activates on numeric measurement values (especially drug doses or concentrations, e.g. “500 µg/ml,” “250 mg/kg,” “20 mU/mL”).

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

cstdint

-0.07

 glam

-0.06

ilor

-0.06

.ic

-0.06

-find

-0.06

ITE

-0.06

ABCDE

-0.06

GRES

-0.06

.tick

-0.06

 Только

-0.06

POSITIVE LOGITS

`<

0.06

<b

0.06

 (),↵

0.06

 starší

0.06

 kỹ

0.06

--

0.06

 составе

0.06

 Having

0.06

gsub

0.06

 Considering

0.06

Activations Density 0.041%

)

The neuron activates on numeric measurement values (especially drug doses or concentrations, e.g. “500 µg/ml,” “250 mg/kg,” “20 mU/mL”).

No Comments

No Known Activations

)

The neuron activates on numeric measurement values (especially drug doses or concentrations, e.g. “500 µg/ml,” “250 mg/kg,” “20 mU/mL”).

No Comments

No Known Activations