INDEX

Explanations

contractions/possessives

np_max-act · gemini-2.0-flash

The neuron spikes on tokens containing apostrophes—i.e. contractions and other clitic forms.

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

 películ

-0.07

-process

-0.07

україн

-0.07

.TRA

-0.06

.initializeApp

-0.06

forest

-0.06

apolis

-0.06

(seconds

-0.06

repositories

-0.06

POSITIVE LOGITS

 gitti

0.08

 peasants

0.06

.undo

0.06

 cela

0.06

 boots

0.06

될

0.06

 इसम

0.06

_TP

0.06

 εκεί

0.06

 dokun

0.06

Activations Density 0.074%

contractions/possessives

The neuron spikes on tokens containing apostrophes—i.e. contractions and other clitic forms.

No Comments

No Known Activations

contractions/possessives

The neuron spikes on tokens containing apostrophes—i.e. contractions and other clitic forms.

No Comments

No Known Activations