INDEX

Explanations

?”

np_max-act · gemini-2.0-flash

This neuron activates on forum navigation or policy-related interface cues (e.g. “Click here,” “posting guidelines,” “policies,” “time-out,” “banning”).

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

รถ

-0.08

 conosc

-0.07

 wallets

-0.06

User

-0.06

 titles

-0.06

_PARAMS

-0.06

 debates

-0.06

 Facility

-0.06

لف

-0.06

_venta

-0.06

POSITIVE LOGITS

 PCIe

0.07

 adlandır

0.07

 Comet

0.07

のに

0.07

.scss

0.06

(engine

0.06

 slick

0.06

Returning

0.06

TION

0.06

 medicinal

0.06

Activations Density 0.001%

?”

This neuron activates on forum navigation or policy-related interface cues (e.g. “Click here,” “posting guidelines,” “policies,” “time-out,” “banning”).

No Comments

No Known Activations