INDEX

Explanations

spin

np_max-act · gemini-2.0-flash

This neuron responds to occurrences of spin-lock operations (e.g. spin_lock/_unlock and their IRQ variants).

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

ITIVE

-0.07

 пер

-0.07

 değerli

-0.06

REF

-0.06

 NOAA

-0.06

similar

-0.06

、彼

-0.06

 Jacobs

-0.06

 McCoy

-0.06

 derived

-0.06

POSITIVE LOGITS

(binding

0.07

][]

0.06

.power

0.06

rna

0.06

_SID

0.06

-eye

0.06

-bar

0.06

say

0.06

ndon

0.06

_once

0.06

Activations Density 0.001%

spin

This neuron responds to occurrences of spin-lock operations (e.g. spin_lock/_unlock and their IRQ variants).

No Comments

No Known Activations