INDEX

Explanations

language

np_max-act · gemini-2.0-flash

The neuron fires specifically on the word “language.”

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

_CUBE

-0.06

 XCTAssertTrue

-0.06

 onPressed

-0.06

OrderId

-0.06

plits

-0.06

PublicKey

-0.06

_encode

-0.06

-find

-0.06

 kills

-0.06

_SINGLE

-0.06

POSITIVE LOGITS

 climate

0.08

 diet

0.07

 mail

0.06

 admin

0.06

Abb

0.06

idi

0.06

 Look

0.06

 abuses

0.06

 Voice

0.06

losing

0.06

Activations Density 0.018%

language

The neuron fires specifically on the word “language.”

No Comments

No Known Activations