INDEX

Explanations

tweak

np_max-act · gemini-2.0-flash

The neuron is strongly activated by Go identifier fragments (CamelCase names and field/type names) in generated source 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

�

-0.07

 services

-0.07

_agents

-0.06

numbers

-0.06

Endian

-0.06

 Fighter

-0.06

.operations

-0.06

行動

-0.06

Planning

-0.06

/id

-0.06

POSITIVE LOGITS

۲۰۲

0.08

Δεν

0.08

ивання

0.07

 Δεν

0.07

	RTLU

0.06

 versa

0.06

vů

0.06

 eslint

0.06

.UNRELATED

0.06

を見

0.06

Activations Density 0.005%

tweak

The neuron is strongly activated by Go identifier fragments (CamelCase names and field/type names) in generated source code.

No Comments

No Known Activations