INDEX

Explanations

find

np_max-act · gemini-2.0-flash

The neuron is keyed to past‐tense action verbs (i.e. verbs ending in “-ed”).

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

	event

-0.07

_processors

-0.07

 decks

-0.07

Dragon

-0.07

.assertIs

-0.06

below

-0.06

 DialogInterface

-0.06

 Jaune

-0.06

ResultsController

-0.06

.currentThread

-0.06

POSITIVE LOGITS

عه

0.06

miyor

0.06

��

0.06

값

0.06

 жод

0.06

 brilliant

0.06

ults

0.06

/bg

0.06

_attr

0.06

不断

0.06

Activations Density 0.551%

find

The neuron is keyed to past‐tense action verbs (i.e. verbs ending in “-ed”).

No Comments

No Known Activations