INDEX

Explanations

has

np_max-act · gemini-2.0-flash

This neuron picks out auxiliary “has” (and associated perfect‐tense verbs) in biographical passages describing someone’s achievements.

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

 سود

-0.07

EventHandler

-0.07

ob

-0.07

 Callable

-0.06

[*

-0.06

_GAME

-0.06

 QPushButton

-0.06

 Psychiat

-0.06

 Brigade

-0.05

採

-0.05

POSITIVE LOGITS

 shorter

0.07

 fertile

0.07

 υπηρε

0.07

 distrust

0.07

cut

0.06

 правила

0.06

átka

0.06

ity

0.06

↵

0.06

fect

0.06

Activations Density 0.026%

has

This neuron picks out auxiliary “has” (and associated perfect‐tense verbs) in biographical passages describing someone’s achievements.

No Comments

No Known Activations