INDEX

Explanations

client

np_max-act · gemini-2.0-flash

The neuron detects mentions of “client(s)”—especially when it appears as a heading or label.

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

ümü

-0.08

ossa

-0.08

meye

-0.07

üsü

-0.07

 Yugoslavia

-0.07

اشته

-0.07

_power

-0.07

وده

-0.07

liste

-0.07

사는

-0.07

POSITIVE LOGITS

 clients

0.10

 Client

0.08

Clients

0.08

 client

0.08

(£

0.07

„ط

0.07

0.06

 Clients

0.06

dí

0.06

_attrib

0.06

Activations Density 0.016%

client

The neuron detects mentions of “client(s)”—especially when it appears as a heading or label.

No Comments

No Known Activations