INDEX

Explanations

budget

np_max-act · gemini-2.0-flash

The neuron activates on low‐cost price descriptors—words like “cheapest,” “cheaper,” “budget,” and “budget‐friendly.”

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

_order

-0.07

 scares

-0.07

_NEXT

-0.06

_PI

-0.06

([]*

-0.06

Oro

-0.06

_member

-0.06

 cerca

-0.06

يمة

-0.06

.nextSibling

-0.06

POSITIVE LOGITS

/public

0.07

 hectic

0.07

 BSON

0.06

 Vanguard

0.06

 Jaguars

0.06

 ugly

0.06

Democratic

0.06

Alternative

0.06

"""↵

0.06

 hareket

0.06

Activations Density 0.010%

budget

The neuron activates on low‐cost price descriptors—words like “cheapest,” “cheaper,” “budget,” and “budget‐friendly.”

No Comments

No Known Activations