INDEX

Explanations

Steam

np_max-act · gemini-2.0-flash

The neuron flags mentions of the Steam platform or related file‐path/install contexts (e.g. “Steam,” “client,” Steam directory names).

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

ensitive

-0.07

Nano

-0.07

.Criteria

-0.07

ẩ

-0.07

Hist

-0.07

 هدف

-0.06

yog

-0.06

teg

-0.06

OUNCE

-0.06

ixture

-0.06

POSITIVE LOGITS

економ

0.07

 fís

0.06

 değişiklik

0.06

ParseException

0.06

ueba

0.06

 Founded

0.06

 deine

0.06

.ReLU

0.06

 inclu

0.06

 stron

0.06

Activations Density 0.016%

Steam

The neuron flags mentions of the Steam platform or related file‐path/install contexts (e.g. “Steam,” “client,” Steam directory names).

No Comments

No Known Activations