INDEX

Explanations

ages

np_max-act · gemini-2.0-flash

The neuron activates on expressions of a person’s age (numerical age followed by “year(s) old”).

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

>");
↵

-0.06

ULATION

-0.06

Args

-0.06

 çıkış

-0.06

lier

-0.06

ıştır

-0.06

 utilisateur

-0.06

imator

-0.06

utton

-0.06

')'

-0.06

POSITIVE LOGITS

تب

0.07

 soph

0.06

(piece

0.06

 solids

0.06

.ResponseEntity

0.06

 displayName

0.06

 Affordable

0.06

 extent

0.06

 associative

0.06

し

0.06

Activations Density 0.025%

ages

The neuron activates on expressions of a person’s age (numerical age followed by “year(s) old”).

No Comments

No Known Activations

ages

The neuron activates on expressions of a person’s age (numerical age followed by “year(s) old”).

No Comments

No Known Activations