INDEX

Explanations

door

np_max-act · gemini-2.0-flash

The neuron detects words describing someone knocking on or opening a door.

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ẳn

-0.06

 Mushroom

-0.06

High

-0.06

chains

-0.06

_tc

-0.06

 removed

-0.06

solution

-0.06

ducer

-0.06

National

-0.05

σα

-0.05

POSITIVE LOGITS

욕

0.06

ดน

0.06

краї

0.06

 ضربه

0.06

�

0.06

.cbo

0.06

 frivol

0.06

 ViewGroup

0.06

�蛛

0.06

Activations Density 0.006%

door

The neuron detects words describing someone knocking on or opening a door.

No Comments

No Known Activations