INDEX

Explanations

std

np_max-act · gemini-2.0-flash

The neuron responds to mentions of the C++ standard‐library namespace (i.e. tokens like “std”).

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

 inquire

-0.07

iator

-0.07

Bag

-0.07

 والح

-0.07

AKE

-0.06

rire

-0.06

 depict

-0.06

irá

-0.06

الح

-0.06

 pole

-0.06

POSITIVE LOGITS

(std

0.12

std

0.10

std

0.10

std

0.09

 according

0.08

STD

0.08

TS

0.08

,std

0.08

 didn

0.08

don

0.07

Activations Density 0.007%

std

The neuron responds to mentions of the C++ standard‐library namespace (i.e. tokens like “std”).

No Comments

No Known Activations