INDEX

Explanations

Polish villages

np_max-act · gemini-2.0-flash

The neuron fires on occurrences of the Polish administrative‐district term “Gmina.”

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

 cycles

-0.07

 вступ

-0.06

 dames

-0.06

ysics

-0.06

 predator

-0.06

 rizik

-0.06

ypse

-0.06

 metric

-0.06

illon

-0.06

 tavs

-0.06

POSITIVE LOGITS

GRA

0.07

 girdi

0.06

enance

0.06

 Gala

0.06

eners

0.06

How

0.06

_FINISH

0.06

े-

0.06

.ibm

0.06

TC

0.06

Activations Density 0.001%

Polish villages

The neuron fires on occurrences of the Polish administrative‐district term “Gmina.”

No Comments

No Known Activations

Polish villages

The neuron fires on occurrences of the Polish administrative‐district term “Gmina.”

No Comments

No Known Activations