INDEX

Explanations

/

np_max-act · gemini-2.0-flash

This neuron activates on decimal‐formatted numeric tokens (i.e. floating-point numbers, especially fractional exponents) in the text.

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

_TEM

-0.06

:v

-0.06

 Arbeit

-0.06

Hip

-0.06

Failure

-0.06

agar

-0.06

/commons

-0.06

 changed

-0.06

_VALUES

-0.06

udios

-0.06

POSITIVE LOGITS

 pohled

0.06

intelligence

0.06

toBeDefined

0.06

 Blanch

0.06

"""
↵
↵

0.06

 jails

0.06

 ноября

0.06

 potions

0.06

盒

0.06

 tint

0.06

Activations Density 0.001%

/

This neuron activates on decimal‐formatted numeric tokens (i.e. floating-point numbers, especially fractional exponents) in the text.

No Comments

No Known Activations