INDEX

Explanations

first-person pronoun

np_max-act · gemini-2.0-flash

The neuron detects first-person self-references (instances of “I” and related personal pronouns) in the text.

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

 thereby

-0.07

 diamonds

-0.06

Toolbar

-0.06

.Runtime

-0.06

quared

-0.06

 prized

-0.06

ifier

-0.06

visions

-0.06

 AppBar

-0.06

BuildContext

-0.06

POSITIVE LOGITS

で

0.07

 Loài

0.07

 пра

0.07

 nitel

0.06

fyz

0.06

McC

0.06

 Ports

0.06

 лікар

0.06

成

0.06

ดา

0.06

Activations Density 0.042%

first-person pronoun

The neuron detects first-person self-references (instances of “I” and related personal pronouns) in the text.

No Comments

No Known Activations