INDEX

Explanations

insert

np_max-act · gemini-2.0-flash

This neuron detects mentions of removable memory‐card components (e.g. memory cards, card adaptors/connectors) and the actions of inserting, receiving, or coupling those cards.

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

URLException

-0.07

XmlElement

-0.07

นเต

-0.07

.te

-0.06

_sock

-0.06

_end

-0.06

ис

-0.06

 культури

-0.06

 patio

-0.06

 adverts

-0.06

POSITIVE LOGITS

 چهار

0.08

防

0.07

 widths

0.07

ратно

0.06

าคาร

0.06

 skewed

0.06

 contextual

0.06

νομ

0.06

-packed

0.06

 Maison

0.06

Activations Density 0.020%

insert

This neuron detects mentions of removable memory‐card components (e.g. memory cards, card adaptors/connectors) and the actions of inserting, receiving, or coupling those cards.

No Comments

No Known Activations