INDEX

Explanations

revolution

np_max-act · gemini-2.0-flash

This neuron activates on the word “Revolution” (and its French equivalent “révolution”), especially in reference to the French Revolution.

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

 interpretation

-0.07

 faced

-0.07

.kr

-0.06

 Wang

-0.06

ă

-0.06

 station

-0.06

 för

-0.06

овор

-0.06

 Cooper

-0.06

=sys

-0.06

POSITIVE LOGITS

 whereby

0.07

lime

0.07

зация

0.06

 özellikleri

0.06

 후기

0.06

.addData

0.06

关于

0.06

 TOOL

0.06

ajan

0.06

MouseClicked

0.06

Activations Density 0.034%

revolution

This neuron activates on the word “Revolution” (and its French equivalent “révolution”), especially in reference to the French Revolution.

No Comments

No Known Activations