INDEX

Explanations

[@

np_max-act · gemini-2.0-flash

The neuron is detecting in-text citation markers and bibliography reference tags (e.g. “[ @… ]” and similar reference codes).

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

آمد

-0.07

 famed

-0.06

 beloved

-0.06

景

-0.06

 disastr

-0.06

equals

-0.06

roke

-0.06

 dosp

-0.06

>=

-0.06

 polling

-0.06

POSITIVE LOGITS

 Fargo

0.07

annies

0.07

 EntityState

0.06

POSITORY

0.06

stdarg

0.06

ABOUT

0.06

】

0.06

증금

0.06

.setEditable

0.06

 Pelosi

0.06

Activations Density 0.004%

[@

The neuron is detecting in-text citation markers and bibliography reference tags (e.g. “[ @… ]” and similar reference codes).

No Comments

No Known Activations