INDEX

Explanations

code elements

np_max-act · gemini-2.0-flash

This neuron fires on code identifiers ending in “Entry,” “Element,” or “Fixture” (e.g. DebugElement, ComponentFixture, EntityEntry, and entry variables).

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

 Favorite

-0.07

 Icons

-0.07

modules

-0.06

®

-0.06

CAT

-0.06

Merge

-0.06

 अर

-0.06

(mem

-0.06

 Four

-0.06

(dist

-0.06

POSITIVE LOGITS

prov

0.07

کا

0.06

 disposed

0.06

 постанов

0.06

ney

0.06

 contribute

0.06

 effic

0.06

irst

0.06

reatment

0.06

ैग

0.06

Activations Density 0.016%

code elements

This neuron fires on code identifiers ending in “Entry,” “Element,” or “Fixture” (e.g. DebugElement, ComponentFixture, EntityEntry, and entry variables).

No Comments

No Known Activations