INDEX

Explanations

composition

np_max-act · gemini-2.0-flash

The neuron fires on the formal specification language of patent claims—especially functional verbs and phrases such as “comprises,” “provided,” “projected,” and similar claim-style descriptors.

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

aps

-0.07

_static

-0.07

IX

-0.06

 Bars

-0.06

PSD

-0.06

set

-0.06

(where

-0.06

 км

-0.06

 inval

-0.06

 choosing

-0.06

POSITIVE LOGITS

 χώ

0.07

(exports

0.06

⠀⠀

0.06

塚

0.06

udson

0.06

 consolidated

0.06

wyn

0.06

 obsession

0.06

oran

0.06

Mom

0.06

Activations Density 0.027%

composition

The neuron fires on the formal specification language of patent claims—especially functional verbs and phrases such as “comprises,” “provided,” “projected,” and similar claim-style descriptors.

No Comments

No Known Activations

composition

The neuron fires on the formal specification language of patent claims—especially functional verbs and phrases such as “comprises,” “provided,” “projected,” and similar claim-style descriptors.

No Comments

No Known Activations