INDEX

Explanations

stdlib

np_max-act · gemini-2.0-flash

This neuron activates on C/C++ `#include` directives (especially standard library header includes).

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

automation

-0.07

วรรณ

-0.06

 стек

-0.06

 DAYS

-0.06

 impeachment

-0.06

Sel

-0.06

 ambassadors

-0.06

crm

-0.06

 bartender

-0.06

Merchant

-0.06

POSITIVE LOGITS

bell

0.07

(void

0.07

 می

0.06

_TILE

0.06

착

0.06

hap

0.06

्म

0.06

apia

0.06

ý

0.06

 toJson

0.06

Activations Density 0.002%

stdlib

This neuron activates on C/C++ `#include` directives (especially standard library header includes).

No Comments

No Known Activations

stdlib

This neuron activates on C/C++ `#include` directives (especially standard library header includes).

No Comments

No Known Activations