INDEX

Explanations

Questions and answers

np_max-act · gemini-2.0-flash

This neuron detects when the text is referring to “URLs” (links) in the context of checking or reporting them.

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

Mc

-0.07

スト

-0.06

//------------------------------------------------------------------------------------------------

-0.06

screens

-0.06

Prime

-0.06

 troubles

-0.06

_conditions

-0.06

극

-0.06

isset

-0.06

POSITIVE LOGITS

tableName

0.07

 retorn

0.06

 صاح

0.06

[=

0.06

τύ

0.06

 Cement

0.06

แหน

0.06

뮤

0.06

acement

0.06

Vs

0.06

Activations Density 0.175%

Questions and answers

This neuron detects when the text is referring to “URLs” (links) in the context of checking or reporting them.

No Comments

No Known Activations