INDEX

Explanations

scientific/technical research

np_max-act · gemini-2.0-flash

The neuron responds to the “param” (and related “perturb”) substring in technical terms—e.g. it fires on words like nonparametric or perturbative.

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

登場

-0.08

orpor

-0.07

oklyn

-0.06

()=="

-0.06

 amazing

-0.06

回

-0.06

Deep

-0.06

获得

-0.06

招

-0.06

WEST

-0.06

POSITIVE LOGITS

 апп

0.07

 uintptr

0.07

 ولی

0.07

(dynamic

0.06

ph

0.06

 удал

0.06

 кост

0.06

 tostring

0.06

_OS

0.06

(Constants

0.06

Activations Density 0.031%

scientific/technical research

The neuron responds to the “param” (and related “perturb”) substring in technical terms—e.g. it fires on words like nonparametric or perturbative.

No Comments

No Known Activations