INDEX

Explanations

URL strings

np_max-act · gemini-2.0-flash

The neuron is detecting colon tokens (":") as they appear in code, especially in Objective-C method signatures and string literals.

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

sơ

-0.07

 اخلاق

-0.07

هره

-0.07

kì

-0.07

 contraseña

-0.07

 رفت

-0.07

 state

-0.06

 Нав

-0.06

 adı

-0.06

 contempor

-0.06

POSITIVE LOGITS

런

0.07

 Maurice

0.06

 equival

0.06

ERENCE

0.06

asn

0.06

 Victory

0.06

_codegen

0.06

іст

0.05

Uph

0.05

 Inch

0.05

Activations Density 0.011%

URL strings

The neuron is detecting colon tokens (":") as they appear in code, especially in Objective-C method signatures and string literals.

No Comments

No Known Activations

URL strings

The neuron is detecting colon tokens (":") as they appear in code, especially in Objective-C method signatures and string literals.

No Comments

No Known Activations