INDEX

Explanations

legal texts

np_max-act · gemini-2.0-flash

This neuron activates on legal citations and references to statutes, codes, reporters, or treatises.

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

设计

-0.07

シュ

-0.07

Kind

-0.07

 Readers

-0.07

 boring

-0.06

Supply

-0.06

 Books

-0.06

ظه

-0.06

UDIO

-0.06

ález

-0.06

POSITIVE LOGITS

osi

0.06

 vagy

0.06

عمال

0.06

 poil

0.06

.wrap

0.06

 σε

0.06

 TreeSet

0.06

.toolStripMenuItem

0.06

 Anglic

0.06

 puis

0.06

Activations Density 0.006%

legal texts

This neuron activates on legal citations and references to statutes, codes, reporters, or treatises.

No Comments

No Known Activations