INDEX

Explanations

varied topics

np_max-act · gemini-2.0-flash

The main thing this neuron does is detect adjectives that describe a chemical’s safety or hazard properties.

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

IAM

-0.06

manent

-0.06

 signatures

-0.06

 anchors

-0.06

	events

-0.06

	headers

-0.06

 entreprene

-0.06

iles

-0.06

doesn

-0.05

 ninguna

-0.05

POSITIVE LOGITS

 Neck

0.07

(request

0.07

 niž

0.07

 Hunting

0.06

_section

0.06

ArgsConstructor

0.06

jspx

0.06

yst

0.06

vertisement

0.06

PMC

0.06

Activations Density 0.112%

varied topics

The main thing this neuron does is detect adjectives that describe a chemical’s safety or hazard properties.

No Comments

No Known Activations