INDEX

Explanations

programming questions

np_max-act · gemini-2.0-flash

This neuron lights up on code-related phrases where the user describes setting or reading string data (e.g. “set … from a URL,” “read my string,” “using echo,” “function.js”), i.e. references to loading or assigning variables in code.

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

麦

-0.08

 nebyla

-0.07

Hot

-0.06

Beauty

-0.06

Tony

-0.06

-status

-0.06

 Ones

-0.06

 Beckham

-0.06

 irresponsible

-0.06

Current

-0.06

POSITIVE LOGITS

Î

0.06

">'.

0.06

━━━━

0.06

 сви

0.06

alement

0.06

 متعدد

0.06

}>

0.06

 الی

0.06

 المج

0.06

ीटर

0.06

Activations Density 0.144%

programming questions

This neuron lights up on code-related phrases where the user describes setting or reading string data (e.g. “set … from a URL,” “read my string,” “using echo,” “function.js”), i.e. references to loading or assigning variables in code.

No Comments

No Known Activations

programming questions

This neuron lights up on code-related phrases where the user describes setting or reading string data (e.g. “set … from a URL,” “read my string,” “using echo,” “function.js”), i.e. references to loading or assigning variables in code.

No Comments

No Known Activations