INDEX

Explanations

probability

np_max-act · gemini-2.0-flash

This neuron activates on the “|” and surrounding symbols in conditional‐probability or Bayes‐rule formulae (e.g. p(x|y), q(z|x), etc.).

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

 Sosyal

-0.06

нання

-0.06

 Panels

-0.06

 Circuit

-0.06

_pet

-0.06

 تبلی

-0.06

ління

-0.06

 pall

-0.06

.getAddress

-0.06

idi

-0.06

POSITIVE LOGITS

终于

0.08

init

0.07

ấu

0.06

，可

0.06

(dm

0.06

 Extraction

0.06

VK

0.06

oyer

0.06

/icon

0.06

，更

0.06

Activations Density 0.008%

probability

This neuron activates on the “|” and surrounding symbols in conditional‐probability or Bayes‐rule formulae (e.g. p(x|y), q(z|x), etc.).

No Comments

No Known Activations