INDEX

Explanations

#:

np_max-act · gemini-2.0-flash

references to programming and technical documentation.

oai_token-act-pair · gpt-4o-mini Triggered by @xinyanhu8

This neuron activates on the “#:” comment markers that introduce source‐file references in gettext PO translation files.

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

 fragments

-0.07

Typ

-0.07

		↵		↵		↵

-0.06

 викон

-0.06

 unintended

-0.06

Capt

-0.06

Certificates

-0.06

StorageSync

-0.06

 thicker

-0.06

 Olive

-0.06

POSITIVE LOGITS

 McKay

0.07

 площад

0.07

nergy

0.07

 Lester

0.06

 modeled

0.06

.call

0.06

py

0.06

.LocalDateTime

0.06

Median

0.06

 Shore

0.06

Activations Density 0.001%

#:

references to programming and technical documentation.

This neuron activates on the “#:” comment markers that introduce source‐file references in gettext PO translation files.

No Comments

No Known Activations