INDEX

Explanations

=>

np_max-act · gemini-2.0-flash

The neuron fires on numeric tokens representing non‐integer (floating-point) values (decimal numbers with fractional parts).

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

 Dent

-0.06

 index

-0.06

 робіт

-0.06

&uuml

-0.06

 weiß

-0.06

 पड़

-0.06

ensus

-0.06

-all

-0.06

iná

-0.06

old

-0.06

POSITIVE LOGITS

 Connectivity

0.07

ώντας

0.06

having

0.06

狗

0.06

 берег

0.06

sl

0.06

ChangeEvent

0.06

 chce

0.06

SuppressLint

0.06

_STOCK

0.06

Activations Density 0.015%

=>

The neuron fires on numeric tokens representing non‐integer (floating-point) values (decimal numbers with fractional parts).

No Comments

No Known Activations