INDEX

Explanations

also

np_max-act · gemini-2.0-flash

This neuron detects hedging/reporting phrases that use “also been” (or “also [verb]”) to introduce known or additional observed effects.

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

.deep

-0.06

opcode

-0.06

ា

-0.06

currency

-0.06

_crc

-0.06

 rollout

-0.06

'https

-0.06

[tmp

-0.06

DST

-0.06

POSITIVE LOGITS

Ac

0.07

_pg

0.07

NIC

0.07

------

0.07

natural

0.06

ुरक

0.06

 licked

0.06

atural

0.06

交易

0.06

 prevent

0.06

Activations Density 0.045%

also

This neuron detects hedging/reporting phrases that use “also been” (or “also [verb]”) to introduce known or additional observed effects.

No Comments

No Known Activations