INDEX

Explanations

Code

np_max-act · gemini-2.0-flash

This neuron activates on fragments of programming identifiers that include underscores (e.g. internal/private API or “__async”-style tokens).

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

ysical

-0.06

 classroom

-0.06

инг

-0.06

 cartridge

-0.06

 accrued

-0.06

scss

-0.06

(_,

-0.06

_kw

-0.06

 Childhood

-0.06

 speed

-0.06

POSITIVE LOGITS

所属

0.07

ؤال

0.07

_Q

0.06

axios

0.06

 Leia

0.06

خ

0.06

通知

0.06

aku

0.06

ами

0.06

rası

0.06

Activations Density 0.099%

Code

This neuron activates on fragments of programming identifiers that include underscores (e.g. internal/private API or “__async”-style tokens).

No Comments

No Known Activations