INDEX

Explanations

block

np_max-act · gemini-2.0-flash

This neuron fires on mentions of “block” (e.g., when referring to a block of code).

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

Et

-0.07

 fullname

-0.07

(iParam

-0.07

Write

-0.07

-name

-0.07

 detta

-0.06

 disturbances

-0.06

 директор

-0.06

idata

-0.06

ють

-0.06

POSITIVE LOGITS

0.07

 الد

0.06

 Mikhail

0.06

 screenSize

0.06

 органи

0.06

boom

0.06

 unnatural

0.06

 bölüm

0.06

 category

0.06

.fasterxml

0.06

Activations Density 0.011%

block

This neuron fires on mentions of “block” (e.g., when referring to a block of code).

No Comments

No Known Activations