INDEX

Explanations

arguments/parameters

np_max-act · gemini-2.0-flash

This neuron detects floating-point numeric values (decimal numbers) 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 surged

-0.07

ीटर

-0.07

zac

-0.07

"math

-0.07

 prec

-0.07

ським

-0.06

riting

-0.06

.Logic

-0.06

ERAL

-0.06

�

-0.06

POSITIVE LOGITS

vro

0.07

 panda

0.07

_responses

0.07

 Arthropoda

0.07

 Locate

0.06

GIT

0.06

_callback

0.06

 locationManager

0.06

 CLICK

0.06

 Martha

0.06

Activations Density 0.001%

arguments/parameters

This neuron detects floating-point numeric values (decimal numbers) in the text.

No Comments

No Known Activations