INDEX

Explanations

.net

np_max-act · gemini-2.0-flash

The neuron specifically detects the token sequence “ADO .NET” (i.e. occurrences of the ADO.NET technology name).

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

 suas

-0.07

 compilers

-0.06

\FrameworkBundle

-0.06

Logs

-0.06

 recur

-0.06

__);↵↵

-0.06

 evac

-0.06

 fonction

-0.06

'}}>

-0.06

 shady

-0.06

POSITIVE LOGITS

 https

0.07

 http

0.07

ometer

0.07

 modèle

0.06

Thousands

0.06

_mat

0.06

 waypoints

0.06

_jump

0.06

dg

0.06

 dạy

0.06

Activations Density 0.000%

.net

The neuron specifically detects the token sequence “ADO .NET” (i.e. occurrences of the ADO.NET technology name).

No Comments

No Known Activations