INDEX

Explanations

per

np_max-act · gemini-2.0-flash

This neuron responds to the phrase “As per,” marking formal attributions or references to external sources or regulations.

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

 containing

-0.06

 Maint

-0.06

ельзя

-0.06

.Writer

-0.06

 econ

-0.06

 donde

-0.06

�

-0.06

۵۰

-0.06

 най

-0.06

 treats

-0.06

POSITIVE LOGITS

完

0.07

,re

0.07

席

0.07

 سف

0.07

 Momentum

0.07

正确

0.06

 portion

0.06

;n

0.06

(tm

0.06

依

0.06

Activations Density 0.005%

per

This neuron responds to the phrase “As per,” marking formal attributions or references to external sources or regulations.

No Comments

No Known Activations