INDEX

Explanations

code

np_max-act · gemini-2.0-flash

The neuron activates on floating-point numeric literals (i.e. numbers containing a decimal point).

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

-working

-0.07

 Vehicles

-0.07

hu

-0.06

 STILL

-0.06

('.')

-0.06

 Buying

-0.06

KS

-0.06

ARNING

-0.06

enqueue

-0.06

getting

-0.06

POSITIVE LOGITS

 myriad

0.07

"Some

0.07

///

0.06

"If

0.06

 unreal

0.06

“It

0.06

orse

0.06

"It

0.06

 dislikes

0.06

 zonder

0.06

Activations Density 0.049%

code

The neuron activates on floating-point numeric literals (i.e. numbers containing a decimal point).

No Comments

No Known Activations

code

The neuron activates on floating-point numeric literals (i.e. numbers containing a decimal point).

No Comments

No Known Activations