INDEX

Explanations

wherein

np_max-act · gemini-2.0-flash

This neuron detects occurrences of the patent-style clause introducer “wherein.”

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

 adresse

-0.07

 мої

-0.07

♀♀

-0.07

 Alban

-0.06

 themselves

-0.06

 Tage

-0.06

lapping

-0.06

 Dance

-0.06

 Claude

-0.06

 ourselves

-0.06

POSITIVE LOGITS

 whereby

0.09

IN

0.08

in

0.07

 wherein

0.07

.ai

0.07

FINAL

0.06

_IF

0.06

DB

0.06

ABB

0.06

stdcall

0.06

Activations Density 0.006%

wherein

This neuron detects occurrences of the patent-style clause introducer “wherein.”

No Comments

No Known Activations

wherein

This neuron detects occurrences of the patent-style clause introducer “wherein.”

No Comments

No Known Activations