INDEX

Explanations

meters

np_max-act · gemini-2.0-flash

The neuron is looking for numeric tokens and unit words that indicate mountain elevations or heights.

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

always

-0.08

	stack

-0.07

گل

-0.07

getList

-0.07

ันก

-0.07

amac

-0.07

_we

-0.06

leg

-0.06

dbus

-0.06

Brightness

-0.06

POSITIVE LOGITS

(NULL

0.08

DEN

0.07

 Cardinal

0.06

ür

0.06

 kissing

0.06

 वर

0.06

 χρόνια

0.06

atholic

0.06

인은

0.06

 numéro

0.05

Activations Density 0.004%

meters

The neuron is looking for numeric tokens and unit words that indicate mountain elevations or heights.

No Comments

No Known Activations