INDEX

Explanations

decision-making

np_max-act · gemini-2.0-flash

This neuron detects words referring to formal governance or administrative actions (e.g., decision-making, setting goals, ensuring effective operation).

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

	unset

-0.07

<input

-0.06

itou

-0.06

avia

-0.06

 underestimate

-0.06

 satisfies

-0.06

heart

-0.06

 Tata

-0.06

/ay

-0.06

	this

-0.06

POSITIVE LOGITS

 primal

0.07

浅

0.07

sup

0.06

.AL

0.06

 وسلم

0.06

�

0.06

.HE

0.06

.Cascade

0.06

.device

0.06

_supp

0.06

Activations Density 0.032%

decision-making

This neuron detects words referring to formal governance or administrative actions (e.g., decision-making, setting goals, ensuring effective operation).

No Comments

No Known Activations