INDEX

Explanations

unincorporated communities

np_max-act · gemini-2.0-flash

The neuron strongly activates on mentions of an “unincorporated community” and its geographic descriptors (e.g., location in a county, state, or country).

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

 Agents

-0.07

encer

-0.07

 agent

-0.06

 Agent

-0.06

-du

-0.06

_assert

-0.06

ots

-0.06

Secure

-0.06

 Generally

-0.06

markers

-0.06

POSITIVE LOGITS

 conglomer

0.07

","

0.06

 здійснення

0.06

TestFixture

0.06

.nil

0.06

変

0.06

 Αν

0.06

',{

0.06

 апп

0.06

 Γι

0.06

Activations Density 0.021%

unincorporated communities

The neuron strongly activates on mentions of an “unincorporated community” and its geographic descriptors (e.g., location in a county, state, or country).

No Comments

No Known Activations

unincorporated communities

The neuron strongly activates on mentions of an “unincorporated community” and its geographic descriptors (e.g., location in a county, state, or country).

No Comments

No Known Activations