INDEX

Explanations

">"

np_max-act · gemini-2.0-flash

The main thing this neuron does is detect HTML list‐structure markup (e.g. `<ul>`, `<li>`, `<a>` in nav bars and menus).

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

bedo

-0.07

kové

-0.06

.goto

-0.06

igo

-0.06

"One

-0.06

LM

-0.06

adc

-0.06

tech

-0.06

 kaldır

-0.06

 hive

-0.06

POSITIVE LOGITS

ty

0.06

 laying

0.06

.started

0.06

玻璃

0.06

 가능한

0.06

mess

0.06

메

0.06

és

0.06

.DataTable

0.06

 Improvement

0.06

Activations Density 0.000%

">"

The main thing this neuron does is detect HTML list‐structure markup (e.g. `<ul>`, `<li>`, `<a>` in nav bars and menus).

No Comments

No Known Activations