INDEX

Explanations

smell

np_max-act · gemini-2.0-flash

This neuron activates on words and phrases related to smelling or odors (e.g., “sniff,” “smell,” “stinks”).

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

Translation

-0.07

]()↵

-0.07

-0.06

Và

-0.06

삶

-0.06

  ↵    ↵

-0.06

 workspace

-0.06

PPP

-0.06

 کمتر

-0.06

 时间

-0.06

POSITIVE LOGITS

 smells

0.09

 sniff

0.07

 smelled

0.07

 smell

0.07

 scent

0.07

 flavor

0.07

 filtered

0.07

entic

0.07

 smelling

0.07

Filter

0.07

Activations Density 0.008%

smell

This neuron activates on words and phrases related to smelling or odors (e.g., “sniff,” “smell,” “stinks”).

No Comments

No Known Activations