INDEX

Explanations

directions

np_max-act · gemini-2.0-flash

This neuron activates on mentions of light being scattered or changing direction—particularly tokens in phrases about scattering “in all directions.”

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

 vhod

-0.06

 less

-0.06

Reach

-0.06

 dread

-0.06

 headset

-0.06

よく

-0.06

_DOCUMENT

-0.06

少女

-0.06

login

-0.06

ем

-0.06

POSITIVE LOGITS

MBER

0.07

.En

0.07

cription

0.07

_cpus

0.06

 Комп

0.06

toFixed

0.06

 Continent

0.06

 Brussels

0.06

 Kentucky

0.06

gan

0.06

Activations Density 0.007%

directions

This neuron activates on mentions of light being scattered or changing direction—particularly tokens in phrases about scattering “in all directions.”

No Comments

No Known Activations

directions

This neuron activates on mentions of light being scattered or changing direction—particularly tokens in phrases about scattering “in all directions.”

No Comments

No Known Activations