INDEX

Explanations

plus or minus

np_max-act · gemini-2.0-flash

This neuron detects decimal‐formatted numeric literals (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

 Planner

-0.06

۳۵

-0.06

 Knoxville

-0.06

 Raphael

-0.06

	volatile

-0.06

ินทาง

-0.06

日期

-0.06

Exposed

-0.06

 shoulders

-0.06

 mailbox

-0.06

POSITIVE LOGITS

?,?,

0.07

.base

0.07

.Mar

0.07

 never

0.07

 Feeling

0.07

터

0.06

never

0.06

арод

0.06

_int

0.06

”?

0.06

Activations Density 0.024%

plus or minus

This neuron detects decimal‐formatted numeric literals (numbers containing a decimal point).

No Comments

No Known Activations

plus or minus

This neuron detects decimal‐formatted numeric literals (numbers containing a decimal point).

No Comments

No Known Activations