INDEX

Explanations

,

np_max-act · gemini-2.0-flash

The neuron activates on words that describe or qualify an object’s ability, capacity, or functionality.

oai_token-act-pair · o4-mini Triggered by @xinyanhu8

character interactions that exhibit flirtation and sensuality.

oai_token-act-pair · gpt-4o-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

Ide

-0.08

 Lean

-0.07

vidence

-0.07

 Americas

-0.07

rice

-0.07

(Camera

-0.06

RAY

-0.06

Nah

-0.06

 redirected

-0.06

 Stam

-0.06

POSITIVE LOGITS

、『

0.07

 nồi

0.06

Bomb

0.06

吉

0.06

 perder

0.06

，不

0.06

한

0.06

 crucial

0.06

************************

0.06

;s

0.06

Activations Density 0.467%

,

The neuron activates on words that describe or qualify an object’s ability, capacity, or functionality.

character interactions that exhibit flirtation and sensuality.

No Comments

No Known Activations

,

The neuron activates on words that describe or qualify an object’s ability, capacity, or functionality.

character interactions that exhibit flirtation and sensuality.

No Comments

No Known Activations