INDEX

Explanations

to

np_max-act · gemini-2.0-flash

This neuron activates on phrasing that describes someone being elected or appointed to a political office.

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

 Λα

-0.07

 parler

-0.06

 спрос

-0.06

láv

-0.06

Expires

-0.06

_GP

-0.06

.Sprintf

-0.06

!='

-0.06

嗎

-0.06

ponses

-0.06

POSITIVE LOGITS

 scalar

0.07

 elected

0.07

 into

0.07

 attorney

0.07

 Academic

0.06

 unload

0.06

SSC

0.06

 Insight

0.06

.factory

0.06

Activations Density 0.011%

to

This neuron activates on phrasing that describes someone being elected or appointed to a political office.

No Comments

No Known Activations