INDEX

Explanations

math equations

np_max-act · gemini-2.0-flash

The neuron fires on single‐letter variable names (like j, p, r, s, etc.) when they appear in algebraic/exponentiation contexts (e.g. as bases or divisors in power or division expressions).

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

enda

-0.07

оло

-0.06

ANGO

-0.06

計

-0.06

Ch

-0.06

-chat

-0.06

ﺔ

-0.06

azine

-0.06

 Rope

-0.06

_value

-0.06

POSITIVE LOGITS

 leicht

0.06

(PHP

0.06

่ะ

0.06

VF

0.06

 incorporation

0.06

のは

0.06

 různých

0.06

kp

0.06

 отримання

0.06

//**↵

0.06

Activations Density 0.003%

math equations

The neuron fires on single‐letter variable names (like j, p, r, s, etc.) when they appear in algebraic/exponentiation contexts (e.g. as bases or divisors in power or division expressions).

No Comments

No Known Activations

math equations

The neuron fires on single‐letter variable names (like j, p, r, s, etc.) when they appear in algebraic/exponentiation contexts (e.g. as bases or divisors in power or division expressions).

No Comments

No Known Activations