INDEX

Explanations

s

np_max-act · gemini-2.0-flash

The neuron detects small tokens representing English clitic suffixes—specifically the apostrophe-t (’t) and apostrophe-s (’s) endings in contractions and possessives.

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

巴

-0.08

城市

-0.07

Lee

-0.07

 Friedrich

-0.07

 Hospitals

-0.07

 seine

-0.06

 rencontres

-0.06

 alumnos

-0.06

chia

-0.06

what

-0.06

POSITIVE LOGITS

�s

0.10

´s

0.09

‘s

0.08

’S

0.08

?s

0.08

�t

0.07

'S

0.07

's

0.06

upply

0.06

(define

0.06

Activations Density 0.013%

s

The neuron detects small tokens representing English clitic suffixes—specifically the apostrophe-t (’t) and apostrophe-s (’s) endings in contractions and possessives.

No Comments

No Known Activations