INDEX

Explanations

college degrees

np_max-act · gemini-2.0-flash

The neuron fires on tokens that are part of academic degree listings (e.g. “Bachelor of Science,” “Master of Science,” “Juris Doctor,” and their numeric qualifiers).

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

 loser

-0.07

Fre

-0.07

یم

-0.07

Coder

-0.07

 friction

-0.07

OCR

-0.07

 director

-0.06

 podr

-0.06

-development

-0.06

느

-0.06

POSITIVE LOGITS

slice

0.07

.setDate

0.06

*math

0.06

apphire

0.06

 그것

0.06

.listBox

0.06

eliness

0.06

 обра

0.06

replaceAll

0.06

.opengl

0.06

Activations Density 0.004%

college degrees

The neuron fires on tokens that are part of academic degree listings (e.g. “Bachelor of Science,” “Master of Science,” “Juris Doctor,” and their numeric qualifiers).

No Comments

No Known Activations