INDEX

Explanations

products

np_max-act · gemini-2.0-flash

The neuron detects mentions of chemical decomposition products or undesirable by-products.

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

 Shaw

-0.07

лами

-0.06

 resc

-0.06

 partido

-0.06

vars

-0.06

trained

-0.06

elsing

-0.06

section

-0.06

 дви

-0.06

 clam

-0.06

POSITIVE LOGITS

ometimes

0.07

duct

0.07

 product

0.07

 sediment

0.07

@register

0.06

big

0.06

requent

0.06

 township

0.06

ADVERTISEMENT

0.06

Activations Density 0.011%

products

The neuron detects mentions of chemical decomposition products or undesirable by-products.

No Comments

No Known Activations