INDEX

Explanations

Technical/Engineering texts

np_max-act · gemini-2.0-flash

The neuron fires on ordinal or hierarchical qualifiers (e.g. “first,” “second,” “macro,” etc.).

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

_dialog

-0.08

Descriptors

-0.07

 formulas

-0.06

 surveyed

-0.06

 method

-0.06

 при

-0.06

utility

-0.06

 Piet

-0.06

�

-0.06

рик

-0.06

POSITIVE LOGITS

\Migration

0.07

丁

0.07

 InputDecoration

0.06

(le

0.06

$config

0.06

_InitStructure

0.06

 새로운

0.06

 WaitForSeconds

0.06

(sound

0.06

PS

0.06

Activations Density 0.309%

Technical/Engineering texts

The neuron fires on ordinal or hierarchical qualifiers (e.g. “first,” “second,” “macro,” etc.).

No Comments

No Known Activations

Technical/Engineering texts

The neuron fires on ordinal or hierarchical qualifiers (e.g. “first,” “second,” “macro,” etc.).

No Comments

No Known Activations