INDEX

Explanations

expected, want

np_max-act · gemini-2.0-flash

This neuron never activates on any input and thus does not detect any specific pattern.

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

encers

-0.07

 sinking

-0.07

 SceneManager

-0.07

 Interaction

-0.07

 Sessions

-0.07

 रह

-0.06

 fık

-0.06

 않았

-0.06

Dean

-0.06

 Flex

-0.06

POSITIVE LOGITS

.cc

0.06

 فت

0.06

 благодаря

0.06

_opacity

0.06

.home

0.06

 усіх

0.05

>')↵

0.05

.soft

0.05

 Menschen

0.05

 implanted

0.05

Activations Density 0.006%

expected, want

This neuron never activates on any input and thus does not detect any specific pattern.

No Comments

No Known Activations