INDEX

Explanations

and

np_max-act · gemini-2.0-flash

The neuron fires on coordinating conjunctions (e.g. “and” or “/or”) in license‐style permission 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

urons

-0.06

_stage

-0.06

ioc

-0.06

sandbox

-0.06

OGRAPH

-0.06

 leuk

-0.06

(ele

-0.06

 three

-0.06

 Maur

-0.06

ografia

-0.06

POSITIVE LOGITS

SOL

0.07

 amatør

0.07

 Willi

0.07

 nevy

0.07

Rus

0.07

.SP

0.06

OAD

0.06

.Fail

0.06

.getTarget

0.06

Biz

0.06

Activations Density 0.003%

and

The neuron fires on coordinating conjunctions (e.g. “and” or “/or”) in license‐style permission text.

No Comments

No Known Activations