INDEX

Explanations

iv

np_max-act · gemini-2.0-flash

The neuron responds to terms indicating insect generation cycles (voltine words like univoltine, bivoltine, polyvoltine, trivoltine, etc.).

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

Ms

-0.07

 مطالعه

-0.07

 renovations

-0.07

 Blonde

-0.07

 السلام

-0.07

 initializes

-0.07

	Initialize

-0.06

との

-0.06

 little

-0.06

 Little

-0.06

POSITIVE LOGITS

 فرمان

0.07

gly

0.07

 setEmail

0.06

raci

0.06

yum

0.06

.documentElement

0.06

共

0.06

≥

0.06

(Service

0.06

lif

0.06

Activations Density 0.055%

iv

The neuron responds to terms indicating insect generation cycles (voltine words like univoltine, bivoltine, polyvoltine, trivoltine, etc.).

No Comments

No Known Activations