INDEX

Explanations

a

np_max-act · gemini-2.0-flash

The neuron fires on the “is a” construction (the copula plus the indefinite article) that introduces a definition or description.

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

.getObject

-0.07

MED

-0.06

.rooms

-0.06

 jihad

-0.06

.currentIndex

-0.06

�

-0.06

Cas

-0.06

ك

-0.06

.eu

-0.06

 Suites

-0.06

POSITIVE LOGITS

(font

0.06

_ten

0.06

cción

0.06

ْد

0.06

 víc

0.06

 Abbey

0.06

orca

0.06

 الدم

0.06

 gameObject

0.06

 milyar

0.06

Activations Density 0.006%

a

The neuron fires on the “is a” construction (the copula plus the indefinite article) that introduces a definition or description.

No Comments

No Known Activations