INDEX

Explanations

vaping

np_max-act · gemini-2.0-flash

product names and descriptions related to vaping devices.

oai_token-act-pair · gpt-4o-mini Triggered by @xinyanhu8

The neuron activates on specific vaping hardware model and product names (e.g., brand names and model identifiers).

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

chunk

-0.07

_remote

-0.06

 Hardcore

-0.06

ैस

-0.06

 hang

-0.06

_DENIED

-0.06

，又

-0.06

 Catalog

-0.06

 Scandin

-0.06

.quiz

-0.06

POSITIVE LOGITS

_FINISH

0.07

 clashes

0.07

物

0.06

.sources

0.06

gesture

0.06

CURRENT

0.06

_fh

0.06

ofday

0.06

开放

0.06

Activations Density 0.007%

vaping

product names and descriptions related to vaping devices.

The neuron activates on specific vaping hardware model and product names (e.g., brand names and model identifiers).

No Comments

No Known Activations