INDEX

Explanations

Data structures

np_max-act · gemini-2.0-flash

The neuron strongly fires on occurrences of “map” (i.e. map/dictionary type declarations or mentions of maps) in code.

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

 chrome

-0.07

.mkdirs

-0.06

 borrowed

-0.06

finite

-0.06

(screen

-0.06

وو

-0.06

 Scoped

-0.06

_partition

-0.06

 Marg

-0.06

orz

-0.06

POSITIVE LOGITS

 incremental

0.07

oui

0.06

 좋은

0.06

Hola

0.06

Break

0.06

Ownership

0.06

 Raqqa

0.06

олнитель

0.06

.nome

0.06

 impeccable

0.06

Activations Density 0.031%

Data structures

The neuron strongly fires on occurrences of “map” (i.e. map/dictionary type declarations or mentions of maps) in code.

No Comments

No Known Activations

Data structures

The neuron strongly fires on occurrences of “map” (i.e. map/dictionary type declarations or mentions of maps) in code.

No Comments

No Known Activations