INDEX

Explanations

d

np_max-act · gemini-2.0-flash

The neuron activates on floating‐point numeric tokens (decimal numbers) typically found in legal citations.

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

 будинку

-0.07

kového

-0.07

шили

-0.06

olf

-0.06

.getFont

-0.06

تیجه

-0.06

 тепер

-0.06

.Level

-0.06

.Driver

-0.06

う

-0.06

POSITIVE LOGITS

Yan

0.07

 roomId

0.07

UDA

0.07

 confidentiality

0.06

 effic

0.06

Fc

0.06

pons

0.06

 Shortcut

0.06

icone

0.06

éc

0.06

Activations Density 0.001%

d

The neuron activates on floating‐point numeric tokens (decimal numbers) typically found in legal citations.

No Comments

No Known Activations