INDEX

Explanations

By itself

np_max-act · gemini-2.0-flash

This neuron activates on phrases describing things resolving or occurring naturally without intervention—most strongly on “on their own.”

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

ใต

-0.07

Het

-0.07

دانلود

-0.06

 Teknik

-0.06

zak

-0.06

kd

-0.06

Hello

-0.06

StateException

-0.06

 Informationen

-0.06

 Polly

-0.06

POSITIVE LOGITS

.norm

0.08

 rhythm

0.07

drink

0.07

still

0.07

	padding

0.07

 beta

0.07

 sugar

0.07

cb

0.06

 хоч

0.06

 friendships

0.06

Activations Density 0.032%

By itself

This neuron activates on phrases describing things resolving or occurring naturally without intervention—most strongly on “on their own.”

No Comments

No Known Activations