INDEX

Explanations

Mentions decades/years

np_max-act · gemini-2.0-flash

The neuron activates on numeric date references—especially four‐digit years.

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.07

-yellow

-0.06

 demand

-0.06

odium

-0.06

-0.05

 tents

-0.05

.Image

-0.05

seb

-0.05

PA

-0.05

released

-0.05

POSITIVE LOGITS

Startup

0.07

yyvsp

0.07

林

0.07

?=.*

0.06

 authDomain

0.06

.align

0.06

سة

0.06

 ساخته

0.06

 glfw

0.06

 gdzie

0.06

Activations Density 0.055%

Mentions decades/years

The neuron activates on numeric date references—especially four‐digit years.

No Comments

No Known Activations

Mentions decades/years

The neuron activates on numeric date references—especially four‐digit years.

No Comments

No Known Activations