INDEX

Explanations

ilot

np_max-act · gemini-2.0-flash

This neuron activates on occurrences of the word “pilot.”

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

 daň

-0.07

 seasonal

-0.07

ishes

-0.07

 Huffman

-0.06

rocessing

-0.06

 textures

-0.06

асс

-0.06

.address

-0.06

 expressions

-0.06

 Moreno

-0.06

POSITIVE LOGITS

 pilot

0.15

 Pilot

0.14

 pilots

0.11

Pil

0.10

pil

0.09

Demo

0.08

ilot

0.08

ilent

0.08

demo

0.08

 lider

0.08

Activations Density 0.005%

ilot

This neuron activates on occurrences of the word “pilot.”

No Comments

No Known Activations