INDEX

Explanations

instructions or recommendations

np_max-act · gemini-2.0-flash

This neuron responds to open-class content words—particularly nouns and verbs conveying key semantic information—while ignoring common function words.

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

 descend

-0.06

 Consort

-0.06

 Algebra

-0.06

Abb

-0.06

 мати

-0.06

 DISPATCH

-0.06

코

-0.06

алась

-0.06

)'↵

-0.06

 explanatory

-0.06

POSITIVE LOGITS

AUD

0.07

_sid

0.06

why

0.06

권

0.06

 زي

0.06

condition

0.06

 supplier

0.06

 ethnicity

0.06

_patient

0.06

 شهری

0.06

Activations Density 0.119%

instructions or recommendations

This neuron responds to open-class content words—particularly nouns and verbs conveying key semantic information—while ignoring common function words.

No Comments

No Known Activations