INDEX

Explanations

Locations

np_max-act · gemini-2.0-flash

The neuron fires on proper‐name tokens denoting places or institutions (e.g. geographic names and university/college titles).

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 измен

-0.07

ฮ

-0.07

 fian

-0.07

illus

-0.06

 počtu

-0.06

 guard

-0.06

 visa

-0.06

 advance

-0.06

HAM

-0.06

，最

-0.06

POSITIVE LOGITS

 Percentage

0.07

働

0.06

.bluetooth

0.06

 accessing

0.06

 whatsoever

0.06

."),↵

0.06

ΙΑ

0.06

ozo

0.06

 trav

0.06

setDescription

0.06

Activations Density 0.026%

Locations

The neuron fires on proper‐name tokens denoting places or institutions (e.g. geographic names and university/college titles).

No Comments

No Known Activations