INDEX

Explanations

votes

np_max-act · gemini-2.0-flash

The neuron is triggered by mentions of legislative or political bodies and their related vote counts or proceedings.

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

 Illustrator

-0.07

minute

-0.07

광고

-0.06

LEVEL

-0.06

 RIGHT

-0.06

arging

-0.06

lemetry

-0.06

ceptor

-0.06

TX

-0.06

POSITIVE LOGITS

 spac

0.07

bose

0.07

 nouvelles

0.06

saida

0.06

 nomin

0.06

_sequences

0.06

واع

0.06

rias

0.06

ocrat

0.06

_compat

0.06

Activations Density 0.034%

votes

The neuron is triggered by mentions of legislative or political bodies and their related vote counts or proceedings.

No Comments

No Known Activations

votes

The neuron is triggered by mentions of legislative or political bodies and their related vote counts or proceedings.

No Comments

No Known Activations