INDEX

Explanations

book excerpts

np_max-act · gemini-2.0-flash

The neuron fires on capitalized content words in titles or headings (e.g., book and article titles).

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

 Gund

-0.07

อร

-0.06

 Franz

-0.06

 Reno

-0.06

سب

-0.06

 tento

-0.06

 özel

-0.06

(_)

-0.06

�

-0.06

til

-0.06

POSITIVE LOGITS

	version

0.07

[+

0.07

 JQuery

0.07

 bastante

0.06

_slope

0.06

SEMB

0.06

Scheme

0.06

########################################

0.06

WWW

0.06

InstanceState

0.06

Activations Density 0.031%

book excerpts

The neuron fires on capitalized content words in titles or headings (e.g., book and article titles).

No Comments

No Known Activations