INDEX

Explanations

punctuation

np_max-act · gemini-2.0-flash

The neuron fires on numeric tokens (including integers, dates, and decimal figures).

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

lor

-0.07

dispatcher

-0.06

 resurrect

-0.06

_SCHEMA

-0.06

units

-0.06

 ENERGY

-0.06

 domic

-0.06

_MODAL

-0.06

alleng

-0.06

 Capac

-0.06

POSITIVE LOGITS

 Locke

0.06

Wie

0.06

目を

0.06

ắ

0.06

얘

0.06

=#

0.06

 vàng

0.06

xm

0.06

 anonym

0.06

vor

0.06

Activations Density 0.036%

punctuation

The neuron fires on numeric tokens (including integers, dates, and decimal figures).

No Comments

No Known Activations