INDEX

Explanations

code

np_max-act · gemini-2.0-flash

The neuron activates on references to an “options” configuration object or method (e.g. tokens like Options, .options, setOptions, mergeData).

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

ucci

-0.07

Psi

-0.07

agogue

-0.06

자를

-0.06

 FileWriter

-0.06

.FILES

-0.06

++.

-0.06

ileri

-0.06

 collections

-0.06

UpperCase

-0.06

POSITIVE LOGITS

WER

0.06

-multi

0.06

_score

0.06

 dazz

0.06

 mare

0.06

 کمی

0.06

 veterinarian

0.06

 Lyons

0.06

 dobr

0.06

Activations Density 0.061%

code

The neuron activates on references to an “options” configuration object or method (e.g. tokens like Options, .options, setOptions, mergeData).

No Comments

No Known Activations