INDEX

Explanations

number 2

np_max-act · gemini-2.0-flash

The neuron fires on numeric tokens—especially standalone numbers or version/sequence indicators in titles.

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

.user

-0.06

Licensed

-0.06

 hurricane

-0.06

 startup

-0.06

(seconds

-0.06

getFullYear

-0.06

 نام

-0.06

Location

-0.06

 всього

-0.06

 días

-0.06

POSITIVE LOGITS

'"

0.08

:///

0.06

ویل

0.06

KD

0.06

 Diane

0.06

umann

0.06

 dioxide

0.06

반

0.06

 deduct

0.06

 قن

0.06

Activations Density 0.019%

number 2

The neuron fires on numeric tokens—especially standalone numbers or version/sequence indicators in titles.

No Comments

No Known Activations

number 2

The neuron fires on numeric tokens—especially standalone numbers or version/sequence indicators in titles.

No Comments

No Known Activations