INDEX

Explanations

distant views and light

np_max-act · gemini-2.0-flash

This neuron responds to words describing visual illumination and atmospheric lighting (torchlight, smoke, flickering lights, sky, glowing).

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

County

-0.07

ім

-0.06

izona

-0.06

기

-0.06

_CPU

-0.06

ิเคราะห

-0.06

 сад

-0.06

monitor

-0.06

onta

-0.06

POSITIVE LOGITS

 newPos

0.07

 immersed

0.06

hav

0.06

 inspiring

0.06

一级

0.06

呀

0.06

程

0.06

 Survivor

0.06

*size

0.06

Activations Density 0.048%

distant views and light

This neuron responds to words describing visual illumination and atmospheric lighting (torchlight, smoke, flickering lights, sky, glowing).

No Comments

No Known Activations