INDEX

Explanations

voltage

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.15.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 primero

-0.08

 кто

-0.07

 prec

-0.07

 fibonacci

-0.07

BIT

-0.07

 Grim

-0.06

 Books

-0.06

담

-0.06

 Explorer

-0.06

 Hands

-0.06

POSITIVE LOGITS

 voltage

0.10

 Voltage

0.08

 volt

0.08

Voltage

0.08

 overhaul

0.07

Volt

0.07

 volatility

0.07

VL

0.07

PDOException

0.07

Activations Density 0.009%

voltage

No Comments

No Known Activations