INDEX

Explanations

oly

np_max-act · gemini-2.0-flash

The neuron fires on the special “Anti GPT” token sequence, i.e. it detects occurrences of the phrase “Anti GPT.”

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

辛

-0.07

่าส

-0.07

 cougar

-0.07

ugas

-0.06

рід

-0.06

.Panel

-0.06

Israeli

-0.06

ศร

-0.06

 pregn

-0.06

POSITIVE LOGITS

 agreeing

0.07

фіка

0.07

，不过

0.06

 ради

0.06

 merely

0.06

 agreed

0.06

__*/

0.06

HOW

0.06

 argued

0.06

 dumpster

0.06

Activations Density 0.000%

oly

The neuron fires on the special “Anti GPT” token sequence, i.e. it detects occurrences of the phrase “Anti GPT.”

No Comments

No Known Activations