INDEX

Explanations

code

np_max-act · gemini-2.0-flash

The neuron fires on code tokens that appear in method/function definitions—annotations like @Override, access modifiers (public), return types (void), and method names (e.g. onCreate).

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

 مجموعه

-0.06

.mc

-0.06

 slova

-0.06

Kol

-0.06

 paddingTop

-0.06

Lý

-0.06

+C

-0.06

sembles

-0.06

DSP

-0.06

 Mär

-0.06

POSITIVE LOGITS

 Helps

0.06

 이는

0.06

'name

0.06

.↵↵↵↵↵↵↵↵

0.06

 owes

0.06

 disparity

0.06

Προ

0.06

 currently

0.06

 їх

0.06

 matchups

0.06

Activations Density 0.074%

code

The neuron fires on code tokens that appear in method/function definitions—annotations like @Override, access modifiers (public), return types (void), and method names (e.g. onCreate).

No Comments

No Known Activations

code

The neuron fires on code tokens that appear in method/function definitions—annotations like @Override, access modifiers (public), return types (void), and method names (e.g. onCreate).

No Comments

No Known Activations