INDEX

Explanations

code and programming

np_max-act · gemini-2.0-flash

The neuron fires on fragments of URIs and file‐resource paths (e.g. “http”, “Images\Koala.jpg”, XML namespaces, ImageBrush paths).

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

romě

-0.07

 rents

-0.07

_SWITCH

-0.07

Massage

-0.06

(receiver

-0.06

Tester

-0.06

_POINTS

-0.06

_checker

-0.06

 Supporters

-0.06

.RemoveAll

-0.06

POSITIVE LOGITS

{EIF

0.06

 recycle

0.06

UAL

0.06

ød

0.06

ونة

0.06

"{

0.06

 unstable

0.06

 аллерг

0.06

 біл

0.06

Activations Density 0.078%

code and programming

The neuron fires on fragments of URIs and file‐resource paths (e.g. “http”, “Images\Koala.jpg”, XML namespaces, ImageBrush paths).

No Comments

No Known Activations