INDEX

Explanations

code output statements

np_max-act · gemini-2.0-flash

The neuron is triggered by calls to printing/logging functions (e.g. console.log, alert, WriteLine, println, trace).

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

rab

-0.07

حه

-0.07

-array

-0.06

 lean

-0.06

Byte

-0.06

orc

-0.06

ğan

-0.06

[Z

-0.06

_LT

-0.06

POSITIVE LOGITS

 kutje

0.06

 createSelector

0.06

 Alternate

0.06

 آسیاب

0.06

用品

0.06

 dolayı

0.06

Nintendo

0.06

 #-}↵↵

0.06

 authDomain

0.06

.showError

0.06

Activations Density 0.032%

code output statements

The neuron is triggered by calls to printing/logging functions (e.g. console.log, alert, WriteLine, println, trace).

No Comments

No Known Activations