INDEX

Explanations

code syntax

np_max-act · gemini-2.0-flash

The neuron fires on namespaced template tags—i.e. XML/HTML‐like elements whose tag names contain a prefix and a colon (for example `<g:set>`, `<g:each>`, `<c:if>`).

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

 disagreements

-0.06

_HW

-0.06

 있어

-0.06

.em

-0.06

 Orbit

-0.06

 Đối

-0.06

 işte

-0.06

FSIZE

-0.06

 удал

-0.06

IBM

-0.06

POSITIVE LOGITS

-testid

0.07

umbling

0.07

 νεφοκάλυψης

0.06

 Pyramid

0.06

TargetException

0.06

.clientHeight

0.06

 anniversary

0.06

.viewer

0.06

사랑

0.06

Rec

0.06

Activations Density 0.010%

code syntax

The neuron fires on namespaced template tags—i.e. XML/HTML‐like elements whose tag names contain a prefix and a colon (for example `<g:set>`, `<g:each>`, `<c:if>`).

No Comments

No Known Activations

code syntax

The neuron fires on namespaced template tags—i.e. XML/HTML‐like elements whose tag names contain a prefix and a colon (for example `<g:set>`, `<g:each>`, `<c:if>`).

No Comments

No Known Activations