INDEX

Explanations

code

np_max-act · gemini-2.0-flash

This neuron activates on Python context‐manager exit method definitions—specifically the signature “def exit(self, exc_type, exc_value, traceback):”

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 داده

-0.07

ในว

-0.07

pch

-0.07

 програми

-0.07

енную

-0.07

 EVENTS

-0.06

ですね

-0.06

_open

-0.06

 발매

-0.06

 TAKE

-0.06

POSITIVE LOGITS

addafi

0.07

 topLevel

0.07

Vil

0.07

Ξ

0.07

(Max

0.06

 kite

0.06

consts

0.06

ائج

0.06

 bure

0.06

pov

0.06

Activations Density 0.001%

code

This neuron activates on Python context‐manager exit method definitions—specifically the signature “def __exit__(self, exc_type, exc_value, traceback):”

No Comments

No Known Activations

This neuron activates on Python context‐manager exit method definitions—specifically the signature “def exit(self, exc_type, exc_value, traceback):”